Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.3542. Min Act: -0.1700
Data Index: 4703104 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.1355. Min Act: -0.1700
Data Index: 6096117 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.1667. Min Act: -0.1700
Data Index: 94646 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.1042. Min Act: -0.1700
Data Index: 5357552 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.0417. Min Act: -0.1700
Data Index: 150304 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.0417. Min Act: -0.1700
Data Index: 8526079 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.0104. Min Act: -0.1700
Data Index: 2644500 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.0104. Min Act: -0.1700
Data Index: 8014203 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3542. Min Range: -4.3542
Max Act: 4.0104. Min Act: -0.1700
Data Index: 609310 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9792. Min Act: -0.1700
Data Index: 406625 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9479. Min Act: -0.1700
Data Index: 1553253 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 7474670 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 2169631 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 5138644 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 6429769 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 6980028 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 8009542 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.8854. Min Act: -0.1700
Data Index: 372328 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.9166. Min Act: -0.1700
Data Index: 5691610 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3542. Min Range: -4.3542
Max Act: 3.8541. Min Act: -0.1700
Data Index: 5540971 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19