Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 7073491 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.8169. Min Act: -0.1700
Data Index: 1554928 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.7544. Min Act: -0.1700
Data Index: 6813590 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.7544. Min Act: -0.1700
Data Index: 816692 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.7231. Min Act: -0.1700
Data Index: 7099914 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 8065906 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.6919. Min Act: -0.1700
Data Index: 5950972 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.6294. Min Act: -0.1700
Data Index: 2019188 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.6606. Min Act: -0.1700
Data Index: 284866 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.6606. Min Act: -0.1700
Data Index: 1116865 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.6294. Min Act: -0.1700
Data Index: 2649142 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 2886639 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 195146 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5981. Min Act: -0.1700
Data Index: 5814880 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 5421222 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 4526857 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 1426680 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 1360678 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5669. Min Act: -0.1700
Data Index: 1006940 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8481. Min Range: -4.8481
Max Act: 4.5356. Min Act: -0.1700
Data Index: 946607 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19