Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.3303. Min Act: -0.1700
Data Index: 3012412 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.2053. Min Act: -0.1700
Data Index: 2841688 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.2053. Min Act: -0.1700
Data Index: 8422088 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.1428. Min Act: -0.1700
Data Index: 770540 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.1428. Min Act: -0.1700
Data Index: 6139853 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.1428. Min Act: -0.1700
Data Index: 4255915 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.1428. Min Act: -0.1700
Data Index: 4889236 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.0178. Min Act: -0.1700
Data Index: 8583805 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.0803. Min Act: -0.1700
Data Index: 2030616 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.0803. Min Act: -0.1700
Data Index: 8308288 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 4213522 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3303. Min Range: -8.3303
Max Act: 8.0178. Min Act: -0.1700
Data Index: 4673394 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 6779745 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.8928. Min Act: -0.1700
Data Index: 3610696 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 5873125 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 448456 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 7737368 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 6934154 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.9553. Min Act: -0.1700
Data Index: 2779410 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3303. Min Range: -8.3303
Max Act: 7.8928. Min Act: -0.1700
Data Index: 3916944 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19