Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.6750. Min Act: -0.1700
Data Index: 5914083 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.6352. Min Act: -0.1700
Data Index: 1551773 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5473. Min Act: -0.1700
Data Index: 8481342 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5313. Min Act: -0.1700
Data Index: 6537246 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.5207. Min Act: -0.1700
Data Index: 6104948 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4767. Min Act: -0.1700
Data Index: 1039472 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4843. Min Act: -0.1700
Data Index: 2105887 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4623. Min Act: -0.1700
Data Index: 3098717 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4657. Min Act: -0.1700
Data Index: 5004684 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4506. Min Act: -0.1700
Data Index: 7293645 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4271. Min Act: -0.1700
Data Index: 1166874 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4126. Min Act: -0.1700
Data Index: 5672030 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4056. Min Act: -0.1700
Data Index: 1427061 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4116. Min Act: -0.1700
Data Index: 2896721 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4200. Min Act: -0.1700
Data Index: 8514954 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4086. Min Act: -0.1700
Data Index: 6102635 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.3976. Min Act: -0.1700
Data Index: 4064758 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4138. Min Act: -0.1700
Data Index: 1970954 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.3936. Min Act: -0.1700
Data Index: 5645261 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.6750. Min Range: -3.6750
Max Act: 3.4136. Min Act: -0.1700
Data Index: 7408685 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full textTruncated
Full Text #19