Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 279 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1302. Min Range: -5.1302
Max Act: 5.1302. Min Act: -0.1700
Data Index: 8131689 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1302. Min Range: -5.1302
Max Act: 5.0365. Min Act: -0.1700
Data Index: 4713523 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9115. Min Act: -0.1700
Data Index: 8129932 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8802. Min Act: -0.1700
Data Index: 201579 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9427. Min Act: -0.1700
Data Index: 407176 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.7240. Min Act: -0.1700
Data Index: 7124517 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.7240. Min Act: -0.1700
Data Index: 1673778 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.6615. Min Act: -0.1700
Data Index: 4259178 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.7240. Min Act: -0.1700
Data Index: 6611010 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.6927. Min Act: -0.1700
Data Index: 320364 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.6927. Min Act: -0.1700
Data Index: 4136671 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.7552. Min Act: -0.1700
Data Index: 6173398 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.6927. Min Act: -0.1700
Data Index: 4838478 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.6615. Min Act: -0.1700
Data Index: 1690079 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.5990. Min Act: -0.1700
Data Index: 3090511 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.6302. Min Act: -0.1700
Data Index: 150318 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.5990. Min Act: -0.1700
Data Index: 8677699 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.5365. Min Act: -0.1700
Data Index: 6364316 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.5052. Min Act: -0.1700
Data Index: 6125832 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.5365. Min Act: -0.1700
Data Index: 117240 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19