Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5136. Min Range: -6.5136
Max Act: 6.5136. Min Act: -0.1700
Data Index: 503560 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5136. Min Range: -6.5136
Max Act: 6.2948. Min Act: -0.1700
Data Index: 6227578 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5136. Min Range: -6.5136
Max Act: 6.2636. Min Act: -0.1700
Data Index: 6453439 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5136. Min Range: -6.5136
Max Act: 6.1698. Min Act: -0.1700
Data Index: 6961440 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5136. Min Range: -6.5136
Max Act: 6.1386. Min Act: -0.1700
Data Index: 3385040 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5136. Min Range: -6.5136
Max Act: 6.0761. Min Act: -0.1700
Data Index: 5290033 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.9823. Min Act: -0.1700
Data Index: 4508480 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.9823. Min Act: -0.1700
Data Index: 7491918 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.8261. Min Act: -0.1700
Data Index: 7001815 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.7948. Min Act: -0.1700
Data Index: 2503282 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 8735263 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3574740 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.7323. Min Act: -0.1700
Data Index: 7683157 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.7011. Min Act: -0.1700
Data Index: 6149028 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.6386. Min Act: -0.1700
Data Index: 5979725 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.6698. Min Act: -0.1700
Data Index: 4079620 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.6386. Min Act: -0.1700
Data Index: 3578286 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.6073. Min Act: -0.1700
Data Index: 5800992 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1725606 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5136. Min Range: -6.5136
Max Act: 5.6073. Min Act: -0.1700
Data Index: 2922231 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19