Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1495. Min Range: -6.1495
Max Act: 6.1495. Min Act: -0.1700
Data Index: 5769894 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1495. Min Range: -6.1495
Max Act: 6.1182. Min Act: -0.1700
Data Index: 7134693 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1495. Min Range: -6.1495
Max Act: 6.0245. Min Act: -0.1700
Data Index: 7361889 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.9932. Min Act: -0.1700
Data Index: 420433 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.9307. Min Act: -0.1700
Data Index: 420427 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8682. Min Act: -0.1700
Data Index: 8717309 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3445510 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7745. Min Act: -0.1700
Data Index: 7340949 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7745. Min Act: -0.1700
Data Index: 4000003 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7745. Min Act: -0.1700
Data Index: 3384434 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7432. Min Act: -0.1700
Data Index: 5162897 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7432. Min Act: -0.1700
Data Index: 8309772 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7432. Min Act: -0.1700
Data Index: 7824072 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.7120. Min Act: -0.1700
Data Index: 2805688 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 1936808 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 8765293 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 7658623 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 3952348 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 1759086 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1495. Min Range: -6.1495
Max Act: 5.6807. Min Act: -0.1700
Data Index: 3713692 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19