Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.8291. Min Act: -0.1700
Data Index: 1935848 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.5791. Min Act: -0.1700
Data Index: 4793366 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.5479. Min Act: -0.1700
Data Index: 5898658 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.2666. Min Act: -0.1700
Data Index: 6286525 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.2666. Min Act: -0.1700
Data Index: 8588681 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.2979. Min Act: -0.1700
Data Index: 596282 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.2666. Min Act: -0.1700
Data Index: 8038458 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.2041. Min Act: -0.1700
Data Index: 3830420 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.1729. Min Act: -0.1700
Data Index: 3802948 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.1729. Min Act: -0.1700
Data Index: 1804406 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.0791. Min Act: -0.1700
Data Index: 5316964 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.0791. Min Act: -0.1700
Data Index: 4272224 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.0479. Min Act: -0.1700
Data Index: 2342604 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.0479. Min Act: -0.1700
Data Index: 7947258 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.0479. Min Act: -0.1700
Data Index: 8302076 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8291. Min Range: -6.8291
Max Act: 6.0166. Min Act: -0.1700
Data Index: 2542781 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8291. Min Range: -6.8291
Max Act: 5.9854. Min Act: -0.1700
Data Index: 8252515 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8291. Min Range: -6.8291
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2739409 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8291. Min Range: -6.8291
Max Act: 5.9854. Min Act: -0.1700
Data Index: 7048159 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8291. Min Range: -6.8291
Max Act: 5.9854. Min Act: -0.1700
Data Index: 2004567 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19