Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1656. Min Range: -7.1656
Max Act: 7.1656. Min Act: -0.1700
Data Index: 1655233 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.8844. Min Act: -0.1700
Data Index: 262679 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.8844. Min Act: -0.1700
Data Index: 6989353 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.8531. Min Act: -0.1700
Data Index: 8361543 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.8219. Min Act: -0.1700
Data Index: 8421861 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.7281. Min Act: -0.1700
Data Index: 8421872 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.7281. Min Act: -0.1700
Data Index: 5927604 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.6969. Min Act: -0.1700
Data Index: 6989341 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6192078 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.6344. Min Act: -0.1700
Data Index: 8415266 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.6344. Min Act: -0.1698
Data Index: 6989358 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.6031. Min Act: -0.1700
Data Index: 1779987 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.5719. Min Act: -0.1700
Data Index: 6213193 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.5406. Min Act: -0.1700
Data Index: 8421866 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.5406. Min Act: -0.1700
Data Index: 4341019 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.5406. Min Act: -0.1700
Data Index: 3766886 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.5094. Min Act: -0.1700
Data Index: 7924004 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1971381 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.4781. Min Act: -0.1700
Data Index: 16209 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1656. Min Range: -7.1656
Max Act: 6.4781. Min Act: -0.1700
Data Index: 1196864 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19