Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 22.4064. Min Range: -22.4064
Max Act: 22.4064. Min Act: -0.1700
Data Index: 2862614 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 22.4064. Min Range: -22.4064
Max Act: 22.0314. Min Act: -0.1700
Data Index: 8571572 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.9064. Min Act: -0.1700
Data Index: 1960014 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.7814. Min Act: -0.1700
Data Index: 789353 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.6564. Min Act: -0.1700
Data Index: 5598295 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.5314. Min Act: -0.1700
Data Index: 7648007 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.5314. Min Act: -0.1700
Data Index: 823092 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.5314. Min Act: -0.1700
Data Index: 4113465 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.4064. Min Act: -0.1700
Data Index: 5109076 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.4064. Min Act: -0.1700
Data Index: 8702910 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.2814. Min Act: -0.1700
Data Index: 7433499 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.4064. Min Act: -0.1700
Data Index: 645786 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.4064. Min Act: -0.1700
Data Index: 461239 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.2814. Min Act: -0.1700
Data Index: 1611048 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.2814. Min Act: -0.1700
Data Index: 5352127 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.2814. Min Act: -0.1700
Data Index: 5928039 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.2814. Min Act: -0.1700
Data Index: 1275858 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.2814. Min Act: -0.1700
Data Index: 3172961 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.1564. Min Act: -0.1700
Data Index: 5049071 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 22.4064. Min Range: -22.4064
Max Act: 21.1564. Min Act: -0.1700
Data Index: 2480776 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19