Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.3164. Min Act: -0.1700
Data Index: 1334988 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.3164. Min Act: -0.1700
Data Index: 6564129 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.2539. Min Act: -0.1700
Data Index: 1596089 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.2227. Min Act: -0.1700
Data Index: 337671 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.1914. Min Act: -0.1700
Data Index: 7421989 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.1602. Min Act: -0.1700
Data Index: 4155011 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.1289. Min Act: -0.1700
Data Index: 2287673 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.1289. Min Act: -0.1700
Data Index: 1314101 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0664. Min Act: -0.1700
Data Index: 2084495 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0977. Min Act: -0.1700
Data Index: 730162 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0664. Min Act: -0.1700
Data Index: 6973400 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0352. Min Act: -0.1700
Data Index: 3043023 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0352. Min Act: -0.1700
Data Index: 1935544 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0352. Min Act: -0.1700
Data Index: 3725931 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0664. Min Act: -0.1700
Data Index: 6867817 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0039. Min Act: -0.1700
Data Index: 2269344 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0352. Min Act: -0.1700
Data Index: 2505281 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3164. Min Range: -5.3164
Max Act: 5.0352. Min Act: -0.1700
Data Index: 8536446 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3164. Min Range: -5.3164
Max Act: 4.9727. Min Act: -0.1700
Data Index: 3112104 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3164. Min Range: -5.3164
Max Act: 4.9727. Min Act: -0.1700
Data Index: 2426605 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19