Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.9086. Min Act: -0.1700
Data Index: 4894938 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.8774. Min Act: -0.1700
Data Index: 8614237 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.8461. Min Act: -0.1700
Data Index: 2692873 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.8149. Min Act: -0.1700
Data Index: 4892477 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.7836. Min Act: -0.1700
Data Index: 3564279 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.7836. Min Act: -0.1700
Data Index: 4078675 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.7524. Min Act: -0.1700
Data Index: 3564283 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.6899. Min Act: -0.1700
Data Index: 5133430 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.7211. Min Act: -0.1700
Data Index: 3564282 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.6899. Min Act: -0.1700
Data Index: 2390458 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.6899. Min Act: -0.1700
Data Index: 8782190 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.6586. Min Act: -0.1700
Data Index: 3225420 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.6586. Min Act: -0.1700
Data Index: 7304563 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5961. Min Act: -0.1700
Data Index: 3564281 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5961. Min Act: -0.1700
Data Index: 3462998 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5961. Min Act: -0.1700
Data Index: 739477 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5336. Min Act: -0.1700
Data Index: 2115150 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5336. Min Act: -0.1700
Data Index: 1982910 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5336. Min Act: -0.1700
Data Index: 2357656 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9086. Min Range: -5.9086
Max Act: 5.5336. Min Act: -0.1700
Data Index: 7941036 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19