Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6632. Min Range: -8.6632
Max Act: 8.6632. Min Act: -0.1700
Data Index: 3788577 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6632. Min Range: -8.6632
Max Act: 8.3507. Min Act: -0.1700
Data Index: 7324839 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6632. Min Range: -8.6632
Max Act: 8.2257. Min Act: -0.1700
Data Index: 7178053 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6632. Min Range: -8.6632
Max Act: 8.0695. Min Act: -0.1700
Data Index: 6601490 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6632. Min Range: -8.6632
Max Act: 8.0070. Min Act: -0.1700
Data Index: 7415285 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.9132. Min Act: -0.1700
Data Index: 3861401 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.9132. Min Act: -0.1700
Data Index: 6641685 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.8820. Min Act: -0.1700
Data Index: 2569122 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.8507. Min Act: -0.1700
Data Index: 1813000 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.8195. Min Act: -0.1700
Data Index: 7465258 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7882. Min Act: -0.1700
Data Index: 6934 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7882. Min Act: -0.1700
Data Index: 4002548 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7882. Min Act: -0.1700
Data Index: 6129729 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7882. Min Act: -0.1700
Data Index: 2926951 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7570. Min Act: -0.1700
Data Index: 7575889 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7570. Min Act: -0.1700
Data Index: 7176097 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7570. Min Act: -0.1700
Data Index: 3256512 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.7257. Min Act: -0.1700
Data Index: 6900620 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.6632. Min Act: -0.1700
Data Index: 3162831 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6632. Min Range: -8.6632
Max Act: 7.6632. Min Act: -0.1700
Data Index: 5384303 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19