Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4939 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0199. Min Range: -5.0199
Max Act: 5.0199. Min Act: -0.1700
Data Index: 6828297 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.9574. Min Act: -0.1700
Data Index: 3030133 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.9261. Min Act: -0.1700
Data Index: 2287391 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.8324. Min Act: -0.1700
Data Index: 8057876 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.8011. Min Act: -0.1700
Data Index: 3619398 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.8011. Min Act: -0.1700
Data Index: 5007475 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7699. Min Act: -0.1700
Data Index: 2034894 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 5083111 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7699. Min Act: -0.1700
Data Index: 6194661 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7699. Min Act: -0.1700
Data Index: 3827140 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7699. Min Act: -0.1700
Data Index: 2418799 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 8603297 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 982840 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 4401896 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 2093043 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 3357146 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 4895538 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7074. Min Act: -0.1700
Data Index: 4903316 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7386. Min Act: -0.1700
Data Index: 2822956 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0199. Min Range: -5.0199
Max Act: 4.7074. Min Act: -0.1700
Data Index: 6968692 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19