Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.8234. Min Act: -0.1700
Data Index: 5261517 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.5421. Min Act: -0.1700
Data Index: 6303243 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.4484. Min Act: -0.1700
Data Index: 3104740 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.3859. Min Act: -0.1700
Data Index: 6908466 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.2609. Min Act: -0.1700
Data Index: 876382 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.2609. Min Act: -0.1700
Data Index: 5107868 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.2296. Min Act: -0.1700
Data Index: 4189327 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.2296. Min Act: -0.1700
Data Index: 1141941 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.1359. Min Act: -0.1700
Data Index: 6787850 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.1359. Min Act: -0.1700
Data Index: 6648106 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.1046. Min Act: -0.1700
Data Index: 5221598 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0421. Min Act: -0.1700
Data Index: 7150929 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 5164700 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 5927031 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 7150930 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 7944310 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 5793549 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 5149091 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8234. Min Range: -6.8234
Max Act: 6.0109. Min Act: -0.1700
Data Index: 8643982 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8234. Min Range: -6.8234
Max Act: 5.9484. Min Act: -0.1700
Data Index: 5371411 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19