Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4475 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.6238. Min Act: -0.1700
Data Index: 2910501 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.3738. Min Act: -0.1700
Data Index: 5999140 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.3425. Min Act: -0.1700
Data Index: 2185029 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.2488. Min Act: -0.1700
Data Index: 1629211 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.1550. Min Act: -0.1700
Data Index: 980622 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.0925. Min Act: -0.1700
Data Index: 753624 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6238. Min Range: -7.6238
Max Act: 7.0613. Min Act: -0.1700
Data Index: 8713304 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.9675. Min Act: -0.1700
Data Index: 1648367 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.9675. Min Act: -0.1700
Data Index: 4689732 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.9675. Min Act: -0.1700
Data Index: 2391217 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.9675. Min Act: -0.1700
Data Index: 8117605 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.9363. Min Act: -0.1700
Data Index: 1390733 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.9050. Min Act: -0.1700
Data Index: 2218331 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8738. Min Act: -0.1700
Data Index: 6960819 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8738. Min Act: -0.1700
Data Index: 6043692 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8738. Min Act: -0.1700
Data Index: 7588962 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8738. Min Act: -0.1700
Data Index: 168904 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8738. Min Act: -0.1700
Data Index: 7503336 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8113. Min Act: -0.1700
Data Index: 7721450 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6238. Min Range: -7.6238
Max Act: 6.8113. Min Act: -0.1700
Data Index: 5067383 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19