Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4749 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.5230. Min Act: -0.1700
Data Index: 6157417 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.3355. Min Act: -0.1700
Data Index: 3031294 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.2730. Min Act: -0.1700
Data Index: 8133027 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.2105. Min Act: -0.1700
Data Index: 4349046 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.1480. Min Act: -0.1700
Data Index: 1919617 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.1480. Min Act: -0.1700
Data Index: 5059882 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5230. Min Range: -12.5230
Max Act: 12.0855. Min Act: -0.1700
Data Index: 2787755 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.9605. Min Act: -0.1700
Data Index: 2546742 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.9605. Min Act: -0.1700
Data Index: 1142020 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8980. Min Act: -0.1700
Data Index: 2244603 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8980. Min Act: -0.1700
Data Index: 5283931 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8980. Min Act: -0.1700
Data Index: 7148502 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8980. Min Act: -0.1700
Data Index: 7381991 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8980. Min Act: -0.1700
Data Index: 8504747 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8355. Min Act: -0.1700
Data Index: 275951 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.8980. Min Act: -0.1700
Data Index: 1919616 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.7730. Min Act: -0.1700
Data Index: 254066 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.6480. Min Act: -0.1700
Data Index: 3576545 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.7105. Min Act: -0.1700
Data Index: 5204279 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5230. Min Range: -12.5230
Max Act: 11.7105. Min Act: -0.1700
Data Index: 2356502 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19