Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.7932. Min Act: -0.1700
Data Index: 5078873 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.4182. Min Act: -0.1700
Data Index: 3765663 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.3244. Min Act: -0.1700
Data Index: 682709 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.3557. Min Act: -0.1700
Data Index: 5181929 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.3244. Min Act: -0.1700
Data Index: 3615220 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.2307. Min Act: -0.1700
Data Index: 8142018 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1994. Min Act: -0.1700
Data Index: 3577131 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1994. Min Act: -0.1700
Data Index: 4491081 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1682. Min Act: -0.1700
Data Index: 8396050 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1369. Min Act: -0.1700
Data Index: 6196157 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1682. Min Act: -0.1700
Data Index: 5110952 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1682. Min Act: -0.1700
Data Index: 1145795 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1369. Min Act: -0.1700
Data Index: 2403824 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5622365 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1057. Min Act: -0.1700
Data Index: 3250754 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.1057. Min Act: -0.1700
Data Index: 875527 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.0744. Min Act: -0.1700
Data Index: 8578536 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5008564 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.0744. Min Act: -0.1700
Data Index: 1564684 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7932. Min Range: -6.7932
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5547381 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19