Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3869 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0611. Min Range: -8.0611
Max Act: 8.0611. Min Act: -0.1700
Data Index: 4848030 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.5298. Min Act: -0.1700
Data Index: 2364315 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.4673. Min Act: -0.1700
Data Index: 4188510 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.3736. Min Act: -0.1700
Data Index: 4549945 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.3111. Min Act: -0.1700
Data Index: 6073257 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.3736. Min Act: -0.1700
Data Index: 4822412 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.3111. Min Act: -0.1700
Data Index: 7424006 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.2486. Min Act: -0.1700
Data Index: 4094754 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.1861. Min Act: -0.1700
Data Index: 4406399 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.1861. Min Act: -0.1700
Data Index: 7705344 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.1548. Min Act: -0.1700
Data Index: 5074358 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.1236. Min Act: -0.1700
Data Index: 2516689 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.0923. Min Act: -0.1700
Data Index: 7839322 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.0923. Min Act: -0.1700
Data Index: 5605663 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.0298. Min Act: -0.1700
Data Index: 6502775 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0611. Min Range: -8.0611
Max Act: 7.0298. Min Act: -0.1700
Data Index: 4944456 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0611. Min Range: -8.0611
Max Act: 6.9986. Min Act: -0.1700
Data Index: 8333701 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0611. Min Range: -8.0611
Max Act: 6.9673. Min Act: -0.1700
Data Index: 3135600 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0611. Min Range: -8.0611
Max Act: 6.9361. Min Act: -0.1700
Data Index: 2392881 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0611. Min Range: -8.0611
Max Act: 6.9361. Min Act: -0.1700
Data Index: 6426311 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19