Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2404 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.8572. Min Act: -0.1700
Data Index: 4882523 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6695. Min Act: -0.1700
Data Index: 4234327 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6695. Min Act: -0.1700
Data Index: 1730542 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.7008. Min Act: -0.1700
Data Index: 3374445 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6695. Min Act: -0.1700
Data Index: 6585609 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6695. Min Act: -0.1700
Data Index: 5221493 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6695. Min Act: -0.1700
Data Index: 5759586 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6382. Min Act: -0.1700
Data Index: 3354082 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6069. Min Act: -0.1700
Data Index: 5509844 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6069. Min Act: -0.1700
Data Index: 4526431 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6069. Min Act: -0.1700
Data Index: 8002061 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6069. Min Act: -0.1700
Data Index: 3614793 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6069. Min Act: -0.1700
Data Index: 3513066 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.6069. Min Act: -0.1700
Data Index: 4903408 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.5756. Min Act: -0.1700
Data Index: 3374446 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.5756. Min Act: -0.1700
Data Index: 186738 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.5756. Min Act: -0.1700
Data Index: 634309 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.5756. Min Act: -0.1700
Data Index: 7844958 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.5756. Min Act: -0.1700
Data Index: 2082923 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8572. Min Range: -3.8572
Max Act: 3.5443. Min Act: -0.1700
Data Index: 3964500 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19