Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.3446. Min Act: -0.1700
Data Index: 1117812 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.2127. Min Act: -0.1700
Data Index: 2009478 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0961. Min Act: -0.1700
Data Index: 8756018 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.1295. Min Act: -0.1700
Data Index: 7731723 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.1462. Min Act: -0.1700
Data Index: 8508394 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.1295. Min Act: -0.1700
Data Index: 8367630 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0625. Min Act: -0.1700
Data Index: 3653527 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0457. Min Act: -0.1700
Data Index: 6201481 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0625. Min Act: -0.1700
Data Index: 3553511 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0120. Min Act: -0.1700
Data Index: 8216905 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0289. Min Act: -0.1700
Data Index: 7178894 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3446. Min Range: -2.3446
Max Act: 1.9782. Min Act: -0.1700
Data Index: 6371751 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3446. Min Range: -2.3446
Max Act: 1.9951. Min Act: -0.1700
Data Index: 6800277 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3446. Min Range: -2.3446
Max Act: 1.9782. Min Act: -0.1700
Data Index: 83231 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3446. Min Range: -2.3446
Max Act: 1.9951. Min Act: -0.1700
Data Index: 8076596 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0120. Min Act: -0.1700
Data Index: 8799681 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0120. Min Act: -0.1700
Data Index: 41562 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3446. Min Range: -2.3446
Max Act: 2.0289. Min Act: -0.1700
Data Index: 5318648 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3446. Min Range: -2.3446
Max Act: 1.9443. Min Act: -0.1700
Data Index: 3999252 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3446. Min Range: -2.3446
Max Act: 1.9612. Min Act: -0.1700
Data Index: 1477586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19