Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4457 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1636. Min Range: -6.1636
Max Act: 6.1636. Min Act: -0.1700
Data Index: 4003307 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.9136. Min Act: -0.1700
Data Index: 6071560 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.8199. Min Act: -0.1700
Data Index: 7030845 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.7261. Min Act: -0.1700
Data Index: 1851928 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.7574. Min Act: -0.1700
Data Index: 8264487 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2380107 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6636. Min Act: -0.1700
Data Index: 3215691 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6949. Min Act: -0.1700
Data Index: 6569030 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6636. Min Act: -0.1700
Data Index: 1514772 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6636. Min Act: -0.1700
Data Index: 7790919 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6324. Min Act: -0.1700
Data Index: 8064443 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6324. Min Act: -0.1700
Data Index: 2219462 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6011. Min Act: -0.1700
Data Index: 6823199 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.5699. Min Act: -0.1700
Data Index: 4660830 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.5699. Min Act: -0.1700
Data Index: 772551 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.5699. Min Act: -0.1700
Data Index: 1400324 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.5699. Min Act: -0.1700
Data Index: 3765745 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.6011. Min Act: -0.1700
Data Index: 3983905 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.5386. Min Act: -0.1700
Data Index: 6027164 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1636. Min Range: -6.1636
Max Act: 5.5386. Min Act: -0.1700
Data Index: 508508 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19