Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2914. Min Range: -5.2914
Max Act: 5.2914. Min Act: -0.1700
Data Index: 5816214 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2914. Min Range: -5.2914
Max Act: 5.0726. Min Act: -0.1700
Data Index: 5234797 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2914. Min Range: -5.2914
Max Act: 5.0414. Min Act: -0.1700
Data Index: 3186899 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2914. Min Range: -5.2914
Max Act: 5.0101. Min Act: -0.1700
Data Index: 5099618 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2914. Min Range: -5.2914
Max Act: 5.0101. Min Act: -0.1700
Data Index: 1940291 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.9789. Min Act: -0.1700
Data Index: 4563820 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2914. Min Range: -5.2914
Max Act: 5.0101. Min Act: -0.1700
Data Index: 6141414 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.9476. Min Act: -0.1700
Data Index: 4486637 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.9164. Min Act: -0.1700
Data Index: 2949780 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.9164. Min Act: -0.1700
Data Index: 5002669 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.9164. Min Act: -0.1700
Data Index: 8561574 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8851. Min Act: -0.1700
Data Index: 802154 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8851. Min Act: -0.1700
Data Index: 8442649 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8539. Min Act: -0.1700
Data Index: 4084348 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8539. Min Act: -0.1700
Data Index: 5234798 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8539. Min Act: -0.1700
Data Index: 3107065 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8539. Min Act: -0.1700
Data Index: 5221029 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.7914. Min Act: -0.1700
Data Index: 2034464 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.8226. Min Act: -0.1700
Data Index: 3498532 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2914. Min Range: -5.2914
Max Act: 4.7914. Min Act: -0.1700
Data Index: 4558953 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19