Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4150 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.3467. Min Act: -0.1700
Data Index: 6876775 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.2842. Min Act: -0.1700
Data Index: 3809288 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.2529. Min Act: -0.1700
Data Index: 8152176 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.2529. Min Act: -0.1700
Data Index: 4983711 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 6304490 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 2536324 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 8765509 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 2692155 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 1713324 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 8384617 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 8423095 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 5585234 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 3840280 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1279. Min Act: -0.1700
Data Index: 1228133 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1279. Min Act: -0.1700
Data Index: 3849985 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.1279. Min Act: -0.1700
Data Index: 5099738 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.0967. Min Act: -0.1700
Data Index: 3562419 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.0967. Min Act: -0.1700
Data Index: 5351498 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.0967. Min Act: -0.1700
Data Index: 1004849 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3467. Min Range: -4.3467
Max Act: 4.0967. Min Act: -0.1700
Data Index: 2844817 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19