Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2621. Min Act: -0.1700
Data Index: 509788 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2730. Min Act: -0.1700
Data Index: 6131452 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2069. Min Act: -0.1700
Data Index: 6643828 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.2141. Min Act: -0.1700
Data Index: 1440372 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1855. Min Act: -0.1700
Data Index: 8826766 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1815. Min Act: -0.1700
Data Index: 4271410 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1133. Min Act: -0.1700
Data Index: 6349208 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1249. Min Act: -0.1700
Data Index: 7813971 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1447. Min Act: -0.1700
Data Index: 668160 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1217. Min Act: -0.1700
Data Index: 276169 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1359. Min Act: -0.1700
Data Index: 4993621 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1243. Min Act: -0.1700
Data Index: 8764950 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1318. Min Act: -0.1700
Data Index: 8347613 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1291. Min Act: -0.1700
Data Index: 6105449 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0676. Min Act: -0.1700
Data Index: 4008868 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1103. Min Act: -0.1700
Data Index: 5847592 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.1404. Min Act: -0.1700
Data Index: 7857410 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0711. Min Act: -0.1700
Data Index: 5570034 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0820. Min Act: -0.1700
Data Index: 5745128 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 5.2730. Min Range: -5.2730
Max Act: 5.0879. Min Act: -0.1700
Data Index: 6618288 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full textTruncated
Full Text #19