Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.9572. Min Act: -0.1700
Data Index: 7568791 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.8321. Min Act: -0.1700
Data Index: 3147489 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.8321. Min Act: -0.1700
Data Index: 4812350 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7695. Min Act: -0.1700
Data Index: 7028420 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7852. Min Act: -0.1700
Data Index: 4477474 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7852. Min Act: -0.1700
Data Index: 3147490 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7695. Min Act: -0.1700
Data Index: 7140616 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7695. Min Act: -0.1700
Data Index: 699013 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7383. Min Act: -0.1700
Data Index: 7336550 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7539. Min Act: -0.1700
Data Index: 3503212 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7383. Min Act: -0.1700
Data Index: 8086412 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7383. Min Act: -0.1700
Data Index: 4207877 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7383. Min Act: -0.1700
Data Index: 694624 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.7070. Min Act: -0.1700
Data Index: 507892 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.6913. Min Act: -0.1700
Data Index: 3922598 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.6757. Min Act: -0.1700
Data Index: 1831522 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.6757. Min Act: -0.1700
Data Index: 6707014 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.6444. Min Act: -0.1700
Data Index: 5940541 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.6600. Min Act: -0.1700
Data Index: 2926691 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9572. Min Range: -3.9572
Max Act: 3.6444. Min Act: -0.1700
Data Index: 3562104 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19