Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.7993. Min Act: -0.1700
Data Index: 768928 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.7681. Min Act: -0.1700
Data Index: 768929 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.7681. Min Act: -0.1700
Data Index: 22432 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.7368. Min Act: -0.1700
Data Index: 3008846 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.6431. Min Act: -0.1700
Data Index: 5119011 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.6431. Min Act: -0.1700
Data Index: 4544326 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.6118. Min Act: -0.1700
Data Index: 5762486 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.6431. Min Act: -0.1700
Data Index: 4266773 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.6118. Min Act: -0.1700
Data Index: 6820228 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5806. Min Act: -0.1700
Data Index: 422823 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5493. Min Act: -0.1700
Data Index: 760872 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5493. Min Act: -0.1700
Data Index: 1832889 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5493. Min Act: -0.1700
Data Index: 4877539 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5493. Min Act: -0.1700
Data Index: 4861376 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5181. Min Act: -0.1700
Data Index: 6795347 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5181. Min Act: -0.1700
Data Index: 5807242 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.5181. Min Act: -0.1700
Data Index: 650764 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.4868. Min Act: -0.1700
Data Index: 4503036 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.4868. Min Act: -0.1700
Data Index: 3727921 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7993. Min Range: -4.7993
Max Act: 4.4868. Min Act: -0.1700
Data Index: 4824517 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19