Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.8133. Min Act: -0.1700
Data Index: 8366216 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7875. Min Act: -0.1700
Data Index: 5384048 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7875. Min Act: -0.1700
Data Index: 7022884 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7703. Min Act: -0.1700
Data Index: 5063844 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7616. Min Act: -0.1700
Data Index: 6886499 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7530. Min Act: -0.1700
Data Index: 4909357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7616. Min Act: -0.1700
Data Index: 6700994 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7530. Min Act: -0.1700
Data Index: 40259 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7530. Min Act: -0.1700
Data Index: 3548224 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7530. Min Act: -0.1700
Data Index: 6036878 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7271. Min Act: -0.1700
Data Index: 532929 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7357. Min Act: -0.1699
Data Index: 3902995 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7357. Min Act: -0.1700
Data Index: 3701358 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7357. Min Act: -0.1700
Data Index: 2767571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7357. Min Act: -0.1700
Data Index: 819823 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7271. Min Act: -0.1700
Data Index: 491125 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7357. Min Act: -0.1699
Data Index: 3225900 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7184. Min Act: -0.1700
Data Index: 5918447 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7271. Min Act: -0.1700
Data Index: 8675685 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8133. Min Range: -1.8133
Max Act: 1.7184. Min Act: -0.1700
Data Index: 2778260 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19