Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4533 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4587. Min Range: -5.4587
Max Act: 5.4587. Min Act: -0.1700
Data Index: 446490 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4587. Min Range: -5.4587
Max Act: 5.3024. Min Act: -0.1700
Data Index: 7644215 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4587. Min Range: -5.4587
Max Act: 5.0524. Min Act: -0.1700
Data Index: 3010986 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.8962. Min Act: -0.1700
Data Index: 720851 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.8649. Min Act: -0.1700
Data Index: 7644210 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.7712. Min Act: -0.1700
Data Index: 1054629 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.7399. Min Act: -0.1700
Data Index: 1774028 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.7712. Min Act: -0.1700
Data Index: 233477 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6462. Min Act: -0.1700
Data Index: 703975 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6462. Min Act: -0.1700
Data Index: 5729204 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6462. Min Act: -0.1700
Data Index: 190432 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6462. Min Act: -0.1700
Data Index: 8245158 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6149. Min Act: -0.1700
Data Index: 3227833 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6149. Min Act: -0.1700
Data Index: 8200511 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6149. Min Act: -0.1700
Data Index: 3976362 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6149. Min Act: -0.1700
Data Index: 2339491 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6149. Min Act: -0.1700
Data Index: 190423 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.6149. Min Act: -0.1700
Data Index: 7351517 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.5837. Min Act: -0.1700
Data Index: 5633614 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4587. Min Range: -5.4587
Max Act: 4.5837. Min Act: -0.1700
Data Index: 6453960 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19