Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.8539. Min Act: -0.1700
Data Index: 6996421 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.4476. Min Act: -0.1700
Data Index: 6709220 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.4164. Min Act: -0.1700
Data Index: 911047 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.3226. Min Act: -0.1700
Data Index: 7336696 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.1976. Min Act: -0.1700
Data Index: 7883523 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.1664. Min Act: -0.1700
Data Index: 2245167 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.1039. Min Act: -0.1700
Data Index: 6823365 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.1039. Min Act: -0.1700
Data Index: 5960895 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.1039. Min Act: -0.1700
Data Index: 4016019 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.1039. Min Act: -0.1700
Data Index: 313350 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0726. Min Act: -0.1700
Data Index: 1714901 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0726. Min Act: -0.1700
Data Index: 3410018 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0414. Min Act: -0.1700
Data Index: 8359024 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0101. Min Act: -0.1700
Data Index: 5699572 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0101. Min Act: -0.1700
Data Index: 2770026 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0101. Min Act: -0.1700
Data Index: 3345241 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8539. Min Range: -6.8539
Max Act: 6.0101. Min Act: -0.1700
Data Index: 1036397 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8539. Min Range: -6.8539
Max Act: 5.9789. Min Act: -0.1700
Data Index: 1631869 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8539. Min Range: -6.8539
Max Act: 5.9789. Min Act: -0.1700
Data Index: 1215077 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8539. Min Range: -6.8539
Max Act: 5.9476. Min Act: -0.1700
Data Index: 1084694 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19