Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.3844. Min Act: -0.1700
Data Index: 7646912 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.1969. Min Act: -0.1700
Data Index: 704942 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.1031. Min Act: -0.1700
Data Index: 6166013 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0094. Min Act: -0.1700
Data Index: 4347896 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0406. Min Act: -0.1700
Data Index: 7655814 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0406. Min Act: -0.1700
Data Index: 8826307 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0094. Min Act: -0.1700
Data Index: 8265189 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0094. Min Act: -0.1700
Data Index: 1382756 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0094. Min Act: -0.1700
Data Index: 8695910 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9781. Min Act: -0.1700
Data Index: 3203347 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3844. Min Range: -6.3844
Max Act: 6.0094. Min Act: -0.1700
Data Index: 248026 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9156. Min Act: -0.1700
Data Index: 45157 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9469. Min Act: -0.1700
Data Index: 6144761 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9469. Min Act: -0.1700
Data Index: 5096434 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9781. Min Act: -0.1700
Data Index: 4153378 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9469. Min Act: -0.1700
Data Index: 3823129 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9156. Min Act: -0.1700
Data Index: 4618202 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9469. Min Act: -0.1700
Data Index: 4586189 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9156. Min Act: -0.1700
Data Index: 1804553 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3844. Min Range: -6.3844
Max Act: 5.9156. Min Act: -0.1700
Data Index: 1327419 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19