Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5307. Min Range: -8.5307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 3604717 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5307. Min Range: -8.5307
Max Act: 8.2182. Min Act: -0.1700
Data Index: 8713817 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.9057. Min Act: -0.1700
Data Index: 920051 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.9057. Min Act: -0.1700
Data Index: 6107 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.8432. Min Act: -0.1700
Data Index: 797120 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.9057. Min Act: -0.1700
Data Index: 913790 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.9057. Min Act: -0.1700
Data Index: 5651442 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.8432. Min Act: -0.1700
Data Index: 666703 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.8432. Min Act: -0.1700
Data Index: 2146315 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 2651775 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 7440734 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 928979 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 7801377 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 4227756 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 8711515 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 8020888 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 6322268 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7807. Min Act: -0.1700
Data Index: 56901 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7182. Min Act: -0.1700
Data Index: 7980480 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5307. Min Range: -8.5307
Max Act: 7.7182. Min Act: -0.1700
Data Index: 975366 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19