Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5215 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4982. Min Range: -8.4982
Max Act: 8.4982. Min Act: -0.1700
Data Index: 6858878 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4982. Min Range: -8.4982
Max Act: 8.2482. Min Act: -0.1700
Data Index: 1451759 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4982. Min Range: -8.4982
Max Act: 8.1857. Min Act: -0.1700
Data Index: 5193028 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4982. Min Range: -8.4982
Max Act: 8.1232. Min Act: -0.1700
Data Index: 690948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.9357. Min Act: -0.1700
Data Index: 3709289 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.9982. Min Act: -0.1700
Data Index: 2613530 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.9357. Min Act: -0.1700
Data Index: 1198935 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.8107. Min Act: -0.1700
Data Index: 8214717 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.8107. Min Act: -0.1700
Data Index: 1326894 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.8107. Min Act: -0.1700
Data Index: 4186349 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.7482. Min Act: -0.1700
Data Index: 5816994 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.7482. Min Act: -0.1700
Data Index: 3095983 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.7482. Min Act: -0.1700
Data Index: 5027067 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.7482. Min Act: -0.1700
Data Index: 1559483 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.6857. Min Act: -0.1700
Data Index: 3087352 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.6857. Min Act: -0.1700
Data Index: 2859109 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.6857. Min Act: -0.1700
Data Index: 4487062 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.6857. Min Act: -0.1700
Data Index: 518675 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.6857. Min Act: -0.1700
Data Index: 625539 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4982. Min Range: -8.4982
Max Act: 7.6232. Min Act: -0.1700
Data Index: 3873864 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19