Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.9093. Min Act: -0.1700
Data Index: 1232623 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.8089. Min Act: -0.1700
Data Index: 8071753 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.7419. Min Act: -0.1700
Data Index: 8328677 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.7524. Min Act: -0.1700
Data Index: 145633 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.7591. Min Act: -0.1700
Data Index: 480612 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.7204. Min Act: -0.1700
Data Index: 7005612 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6844. Min Act: -0.1700
Data Index: 5199163 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6845. Min Act: -0.1700
Data Index: 690709 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6684. Min Act: -0.1700
Data Index: 6969955 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6966. Min Act: -0.1700
Data Index: 3173072 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6802. Min Act: -0.1700
Data Index: 7529439 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6750. Min Act: -0.1700
Data Index: 8581635 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6771. Min Act: -0.1700
Data Index: 8660387 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6538. Min Act: -0.1700
Data Index: 6958339 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6441. Min Act: -0.1700
Data Index: 790218 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6532. Min Act: -0.1700
Data Index: 4382804 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6457. Min Act: -0.1700
Data Index: 8138024 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6391. Min Act: -0.1700
Data Index: 2667981 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6202. Min Act: -0.1700
Data Index: 4526274 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.9093. Min Range: -3.9093
Max Act: 3.6235. Min Act: -0.1700
Data Index: 5694316 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full textTruncated
Full Text #19