Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1278 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0173. Min Range: -6.0173
Max Act: 6.0173. Min Act: -0.1700
Data Index: 4575363 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.6736. Min Act: -0.1700
Data Index: 6934468 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.6423. Min Act: -0.1700
Data Index: 7854028 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.6111. Min Act: -0.1700
Data Index: 7716840 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.5173. Min Act: -0.1700
Data Index: 7994012 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.4861. Min Act: -0.1700
Data Index: 3186848 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.4548. Min Act: -0.1700
Data Index: 4026485 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.4236. Min Act: -0.1700
Data Index: 3918110 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.4236. Min Act: -0.1700
Data Index: 6936146 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3923. Min Act: -0.1700
Data Index: 2738149 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3923. Min Act: -0.1700
Data Index: 4811229 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3298. Min Act: -0.1700
Data Index: 7881985 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3611. Min Act: -0.1700
Data Index: 6931201 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3298. Min Act: -0.1700
Data Index: 3940208 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.2986. Min Act: -0.1700
Data Index: 4327420 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3298. Min Act: -0.1700
Data Index: 8369912 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.3298. Min Act: -0.1700
Data Index: 5460949 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.2986. Min Act: -0.1700
Data Index: 8293439 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.2986. Min Act: -0.1700
Data Index: 3609924 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0173. Min Range: -6.0173
Max Act: 5.2986. Min Act: -0.1700
Data Index: 3888481 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19