Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0544. Min Range: -6.0544
Max Act: 6.0544. Min Act: -0.1700
Data Index: 7282105 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.8669. Min Act: -0.1700
Data Index: 5005519 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.8356. Min Act: -0.1700
Data Index: 2862739 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.6481. Min Act: -0.1700
Data Index: 1337100 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.6481. Min Act: -0.1700
Data Index: 8803833 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.6481. Min Act: -0.1700
Data Index: 4576054 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.6169. Min Act: -0.1700
Data Index: 7344230 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5544. Min Act: -0.1700
Data Index: 48923 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5544. Min Act: -0.1700
Data Index: 585569 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5544. Min Act: -0.1700
Data Index: 7161376 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5544. Min Act: -0.1700
Data Index: 5734184 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5544. Min Act: -0.1700
Data Index: 7881804 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5231. Min Act: -0.1700
Data Index: 3039544 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5231. Min Act: -0.1700
Data Index: 5360548 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5231. Min Act: -0.1700
Data Index: 2132765 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5231. Min Act: -0.1700
Data Index: 7147951 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.5231. Min Act: -0.1700
Data Index: 581571 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.4606. Min Act: -0.1700
Data Index: 7110241 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.4919. Min Act: -0.1700
Data Index: 3815120 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0544. Min Range: -6.0544
Max Act: 5.4606. Min Act: -0.1700
Data Index: 48350 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19