Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.4726. Min Act: -0.1700
Data Index: 5615066 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.4101. Min Act: -0.1700
Data Index: 4238912 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.3789. Min Act: -0.1700
Data Index: 6040656 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.2539. Min Act: -0.1700
Data Index: 3737956 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.2226. Min Act: -0.1700
Data Index: 1611186 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.2226. Min Act: -0.1700
Data Index: 4032919 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.1601. Min Act: -0.1700
Data Index: 4238913 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0976. Min Act: -0.1700
Data Index: 3961301 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4647065 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0664. Min Act: -0.1700
Data Index: 7068779 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0351. Min Act: -0.1700
Data Index: 4979183 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0039. Min Act: -0.1700
Data Index: 2489287 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0039. Min Act: -0.1700
Data Index: 4558034 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9726. Min Act: -0.1700
Data Index: 3693 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4726. Min Range: -7.4726
Max Act: 7.0039. Min Act: -0.1700
Data Index: 5000786 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9414. Min Act: -0.1700
Data Index: 779505 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9414. Min Act: -0.1700
Data Index: 2034066 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9101. Min Act: -0.1700
Data Index: 6204260 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9101. Min Act: -0.1700
Data Index: 5646553 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4726. Min Range: -7.4726
Max Act: 6.9101. Min Act: -0.1700
Data Index: 1161856 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19