Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0570. Min Range: -7.0570
Max Act: 7.0570. Min Act: -0.1700
Data Index: 288433 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.7757. Min Act: -0.1700
Data Index: 1532019 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.7132. Min Act: -0.1700
Data Index: 4806379 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.5570. Min Act: -0.1700
Data Index: 2499327 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.4007. Min Act: -0.1700
Data Index: 5112906 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.4320. Min Act: -0.1700
Data Index: 5811253 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.4320. Min Act: -0.1700
Data Index: 5542357 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.4007. Min Act: -0.1700
Data Index: 5660735 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.4320. Min Act: -0.1700
Data Index: 821921 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.4007. Min Act: -0.1700
Data Index: 5475268 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3382. Min Act: -0.1700
Data Index: 7735125 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3382. Min Act: -0.1700
Data Index: 4373173 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3382. Min Act: -0.1700
Data Index: 6442782 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 1934757 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 682217 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 265555 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 521781 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3382. Min Act: -0.1700
Data Index: 1970795 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 2020509 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0570. Min Range: -7.0570
Max Act: 6.3070. Min Act: -0.1700
Data Index: 6596783 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19