Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.8523. Min Act: -0.1700
Data Index: 3329717 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.6023. Min Act: -0.1700
Data Index: 263225 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.5086. Min Act: -0.1700
Data Index: 5743546 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.4461. Min Act: -0.1700
Data Index: 588901 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.3836. Min Act: -0.1700
Data Index: 8405984 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.3836. Min Act: -0.1700
Data Index: 2886628 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.3836. Min Act: -0.1700
Data Index: 6612890 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.3523. Min Act: -0.1700
Data Index: 2365119 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.3211. Min Act: -0.1700
Data Index: 4190981 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.2898. Min Act: -0.1700
Data Index: 544216 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.3211. Min Act: -0.1700
Data Index: 1473180 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.2586. Min Act: -0.1700
Data Index: 5346454 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.2273. Min Act: -0.1700
Data Index: 5206194 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.1961. Min Act: -0.1700
Data Index: 2303862 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.1961. Min Act: -0.1700
Data Index: 4850793 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.1336. Min Act: -0.1700
Data Index: 5641405 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.1648. Min Act: -0.1700
Data Index: 1172318 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.1023. Min Act: -0.1700
Data Index: 7330542 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.1336. Min Act: -0.1700
Data Index: 2195551 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8523. Min Range: -5.8523
Max Act: 5.0711. Min Act: -0.1700
Data Index: 184110 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19