Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.4020. Min Act: -0.1700
Data Index: 1470110 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.2770. Min Act: -0.1700
Data Index: 2561304 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.1208. Min Act: -0.1700
Data Index: 4069488 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.1208. Min Act: -0.1700
Data Index: 2557620 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 4623921 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 280316 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0583. Min Act: -0.1700
Data Index: 3652715 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0583. Min Act: -0.1700
Data Index: 7171639 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0583. Min Act: -0.1700
Data Index: 2775352 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0895. Min Act: -0.1700
Data Index: 1108567 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0583. Min Act: -0.1700
Data Index: 3483476 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0270. Min Act: -0.1700
Data Index: 4139971 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0583. Min Act: -0.1700
Data Index: 3685638 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0270. Min Act: -0.1700
Data Index: 1470122 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4020. Min Range: -6.4020
Max Act: 6.0270. Min Act: -0.1700
Data Index: 8722714 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2005932 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2775354 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2714028 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9333. Min Act: -0.1700
Data Index: 5614865 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4020. Min Range: -6.4020
Max Act: 5.9645. Min Act: -0.1700
Data Index: 7125958 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19