Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6182. Min Range: -7.6182
Max Act: 7.6182. Min Act: -0.1700
Data Index: 3121609 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6182. Min Range: -7.6182
Max Act: 7.1182. Min Act: -0.1700
Data Index: 1799453 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6182. Min Range: -7.6182
Max Act: 7.0557. Min Act: -0.1700
Data Index: 1979269 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.8995. Min Act: -0.1700
Data Index: 4760955 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.8370. Min Act: -0.1700
Data Index: 3121608 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.8057. Min Act: -0.1700
Data Index: 8194283 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.8370. Min Act: -0.1700
Data Index: 324558 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.8057. Min Act: -0.1700
Data Index: 8435600 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7432. Min Act: -0.1700
Data Index: 7362010 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7432. Min Act: -0.1700
Data Index: 5481469 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7745. Min Act: -0.1700
Data Index: 625499 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7120. Min Act: -0.1700
Data Index: 3793452 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7120. Min Act: -0.1700
Data Index: 1769730 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7120. Min Act: -0.1700
Data Index: 8163514 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7432. Min Act: -0.1700
Data Index: 7189757 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.7120. Min Act: -0.1700
Data Index: 1935872 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.6807. Min Act: -0.1700
Data Index: 7510708 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.6807. Min Act: -0.1700
Data Index: 2246854 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.6182. Min Act: -0.1700
Data Index: 6768758 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6182. Min Range: -7.6182
Max Act: 6.6807. Min Act: -0.1700
Data Index: 4431889 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19