Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.3757. Min Act: -0.1700
Data Index: 983111 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.3132. Min Act: -0.1700
Data Index: 6153138 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.2820. Min Act: -0.1700
Data Index: 14269 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.1570. Min Act: -0.1700
Data Index: 2893928 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0945. Min Act: -0.1700
Data Index: 8037381 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0632. Min Act: -0.1700
Data Index: 5723545 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0632. Min Act: -0.1700
Data Index: 3948871 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0007. Min Act: -0.1700
Data Index: 8324226 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0007. Min Act: -0.1700
Data Index: 7061296 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0007. Min Act: -0.1700
Data Index: 6460492 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3757. Min Range: -6.3757
Max Act: 6.0007. Min Act: -0.1700
Data Index: 2753405 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.9695. Min Act: -0.1700
Data Index: 1437485 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.9695. Min Act: -0.1700
Data Index: 7510986 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.9382. Min Act: -0.1700
Data Index: 3385057 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.9695. Min Act: -0.1700
Data Index: 5719683 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.9382. Min Act: -0.1700
Data Index: 3064368 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.9070. Min Act: -0.1700
Data Index: 73747 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.8757. Min Act: -0.1700
Data Index: 6267561 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.8757. Min Act: -0.1700
Data Index: 3533433 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3757. Min Range: -6.3757
Max Act: 5.8757. Min Act: -0.1700
Data Index: 6248886 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19