Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4179. Min Range: -7.4179
Max Act: 7.4179. Min Act: -0.1700
Data Index: 8626238 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4179. Min Range: -7.4179
Max Act: 7.2929. Min Act: -0.1700
Data Index: 3245905 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4179. Min Range: -7.4179
Max Act: 7.2616. Min Act: -0.1700
Data Index: 6364077 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4179. Min Range: -7.4179
Max Act: 7.1991. Min Act: -0.1700
Data Index: 2429992 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4179. Min Range: -7.4179
Max Act: 7.0116. Min Act: -0.1700
Data Index: 1117074 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4179. Min Range: -7.4179
Max Act: 7.0116. Min Act: -0.1700
Data Index: 522018 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.9804. Min Act: -0.1700
Data Index: 3954318 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.9491. Min Act: -0.1700
Data Index: 1900678 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.9179. Min Act: -0.1700
Data Index: 3482330 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.9179. Min Act: -0.1700
Data Index: 4460594 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.9179. Min Act: -0.1700
Data Index: 6679733 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.8866. Min Act: -0.1700
Data Index: 2435920 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.8866. Min Act: -0.1700
Data Index: 780229 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.8554. Min Act: -0.1700
Data Index: 3724407 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.8554. Min Act: -0.1700
Data Index: 8768889 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.8241. Min Act: -0.1700
Data Index: 3284206 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.7929. Min Act: -0.1700
Data Index: 4840673 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.7929. Min Act: -0.1700
Data Index: 4144638 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.7929. Min Act: -0.1700
Data Index: 6522565 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4179. Min Range: -7.4179
Max Act: 6.7616. Min Act: -0.1700
Data Index: 3650855 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19