Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.6053. Min Act: -0.1700
Data Index: 3442748 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4803. Min Act: -0.1700
Data Index: 3309178 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4491. Min Act: -0.1700
Data Index: 7393672 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4491. Min Act: -0.1700
Data Index: 2886183 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3866. Min Act: -0.1700
Data Index: 3160003 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 6972090 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 4387498 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 5504331 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3241. Min Act: -0.1700
Data Index: 1564317 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3241. Min Act: -0.1700
Data Index: 7674446 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3241. Min Act: -0.1700
Data Index: 7671262 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2928. Min Act: -0.1700
Data Index: 3944049 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3241. Min Act: -0.1700
Data Index: 4947207 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2928. Min Act: -0.1700
Data Index: 4338022 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2616. Min Act: -0.1700
Data Index: 4484823 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2616. Min Act: -0.1700
Data Index: 2952587 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2303. Min Act: -0.1700
Data Index: 733100 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.1991. Min Act: -0.1700
Data Index: 4444264 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2303. Min Act: -0.1700
Data Index: 5516604 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.2303. Min Act: -0.1700
Data Index: 6588296 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19