Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4704 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.8895. Min Act: -0.1700
Data Index: 8097348 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.7645. Min Act: -0.1700
Data Index: 5244181 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.5145. Min Act: -0.1700
Data Index: 5266607 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.2645. Min Act: -0.1700
Data Index: 8097349 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.1395. Min Act: -0.1700
Data Index: 5282517 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.1395. Min Act: -0.1700
Data Index: 8477479 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.0145. Min Act: -0.1700
Data Index: 3332592 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.0145. Min Act: -0.1700
Data Index: 395281 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.8895. Min Act: -0.1700
Data Index: 7829765 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.8895. Min Act: -0.1700
Data Index: 7974696 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.8895. Min Range: -19.8895
Max Act: 19.0145. Min Act: -0.1700
Data Index: 3704663 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.8895. Min Act: -0.1700
Data Index: 3295857 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.7645. Min Act: -0.1700
Data Index: 3033576 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.7645. Min Act: -0.1700
Data Index: 2967999 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.7645. Min Act: -0.1700
Data Index: 6902253 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.7645. Min Act: -0.1700
Data Index: 4424665 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.6395. Min Act: -0.1700
Data Index: 4877147 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.7645. Min Act: -0.1700
Data Index: 5847356 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.7645. Min Act: -0.1700
Data Index: 2549464 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.8895. Min Range: -19.8895
Max Act: 18.6395. Min Act: -0.1700
Data Index: 4877146 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19