Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5369 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3240. Min Range: -7.3240
Max Act: 7.3240. Min Act: -0.1700
Data Index: 7989671 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3240. Min Range: -7.3240
Max Act: 7.0740. Min Act: -0.1700
Data Index: 8336905 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3240. Min Range: -7.3240
Max Act: 7.0428. Min Act: -0.1700
Data Index: 1655719 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3240. Min Range: -7.3240
Max Act: 7.0428. Min Act: -0.1700
Data Index: 1022256 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.9490. Min Act: -0.1700
Data Index: 191092 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.9803. Min Act: -0.1700
Data Index: 5092541 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8553. Min Act: -0.1700
Data Index: 1226190 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8865. Min Act: -0.1700
Data Index: 5348359 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8865. Min Act: -0.1700
Data Index: 7851208 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8553. Min Act: -0.1700
Data Index: 3636879 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8553. Min Act: -0.1700
Data Index: 4594476 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8240. Min Act: -0.1700
Data Index: 4638266 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.8240. Min Act: -0.1700
Data Index: 5485553 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7928. Min Act: -0.1700
Data Index: 5501898 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7928. Min Act: -0.1700
Data Index: 76024 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7615. Min Act: -0.1700
Data Index: 5092551 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7303. Min Act: -0.1700
Data Index: 7692831 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7303. Min Act: -0.1700
Data Index: 2847270 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7303. Min Act: -0.1700
Data Index: 3851331 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3240. Min Range: -7.3240
Max Act: 6.7303. Min Act: -0.1700
Data Index: 7628042 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19