Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 991 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6691. Min Range: -8.6691
Max Act: 8.6691. Min Act: -0.1700
Data Index: 7080224 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6691. Min Range: -8.6691
Max Act: 8.1066. Min Act: -0.1700
Data Index: 3676751 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6691. Min Range: -8.6691
Max Act: 8.1691. Min Act: -0.1700
Data Index: 4944039 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.9191. Min Act: -0.1700
Data Index: 507859 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.8566. Min Act: -0.1700
Data Index: 855691 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.8566. Min Act: -0.1700
Data Index: 8268532 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.7941. Min Act: -0.1700
Data Index: 5153161 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.7941. Min Act: -0.1700
Data Index: 6188033 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.7941. Min Act: -0.1700
Data Index: 7717587 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.6691. Min Act: -0.1700
Data Index: 4439092 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.6691. Min Act: -0.1700
Data Index: 5333822 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.6691. Min Act: -0.1700
Data Index: 5295733 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.5441. Min Act: -0.1700
Data Index: 404902 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.6066. Min Act: -0.1700
Data Index: 3931462 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.5441. Min Act: -0.1700
Data Index: 617681 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.5441. Min Act: -0.1700
Data Index: 4294315 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.4816. Min Act: -0.1700
Data Index: 2329126 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.5441. Min Act: -0.1700
Data Index: 4630025 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.4816. Min Act: -0.1700
Data Index: 1486440 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6691. Min Range: -8.6691
Max Act: 7.6066. Min Act: -0.1700
Data Index: 6125678 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19