Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0426. Min Range: -5.0426
Max Act: 5.0426. Min Act: -0.1700
Data Index: 4244684 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.7926. Min Act: -0.1700
Data Index: 3747886 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.6051. Min Act: -0.1700
Data Index: 8662744 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.6051. Min Act: -0.1700
Data Index: 1307372 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.6051. Min Act: -0.1700
Data Index: 984564 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5739. Min Act: -0.1700
Data Index: 2245835 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5739. Min Act: -0.1700
Data Index: 5864656 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5739. Min Act: -0.1700
Data Index: 5390443 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5739. Min Act: -0.1700
Data Index: 6357167 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5426. Min Act: -0.1700
Data Index: 3474187 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5739. Min Act: -0.1700
Data Index: 8662751 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5426. Min Act: -0.1700
Data Index: 686115 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5426. Min Act: -0.1700
Data Index: 2214008 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5114. Min Act: -0.1700
Data Index: 282580 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5114. Min Act: -0.1700
Data Index: 3474195 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.4801. Min Act: -0.1700
Data Index: 686107 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.5114. Min Act: -0.1700
Data Index: 7329250 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.4801. Min Act: -0.1700
Data Index: 2900767 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.4489. Min Act: -0.1700
Data Index: 1537508 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0426. Min Range: -5.0426
Max Act: 4.4489. Min Act: -0.1700
Data Index: 6364865 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19