Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.4040. Min Act: -0.1700
Data Index: 3856211 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.3726. Min Act: -0.1700
Data Index: 428290 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.3726. Min Act: -0.1700
Data Index: 428287 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.3726. Min Act: -0.1700
Data Index: 428278 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.3412. Min Act: -0.1700
Data Index: 3856212 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.3098. Min Act: -0.1700
Data Index: 428293 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2784. Min Act: -0.1700
Data Index: 4630639 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2784. Min Act: -0.1700
Data Index: 4739734 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2941. Min Act: -0.1700
Data Index: 448014 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2627. Min Act: -0.1700
Data Index: 8295321 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2313. Min Act: -0.1700
Data Index: 7238145 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2313. Min Act: -0.1700
Data Index: 7253168 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2156. Min Act: -0.1700
Data Index: 5822538 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2156. Min Act: -0.1700
Data Index: 6675323 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.1841. Min Act: -0.1700
Data Index: 428286 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.2156. Min Act: -0.1700
Data Index: 6985495 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.1841. Min Act: -0.1700
Data Index: 6081637 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.1841. Min Act: -0.1700
Data Index: 7615136 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.1841. Min Act: -0.1700
Data Index: 6482454 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4040. Min Range: -3.4040
Max Act: 3.1841. Min Act: -0.1700
Data Index: 2282573 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19