Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.4958. Min Act: -0.1700
Data Index: 401044 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.4021. Min Act: -0.1700
Data Index: 7177430 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3708. Min Act: -0.1700
Data Index: 4614267 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3708. Min Act: -0.1700
Data Index: 6470837 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3396. Min Act: -0.1700
Data Index: 7353483 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3708. Min Act: -0.1700
Data Index: 173208 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3396. Min Act: -0.1700
Data Index: 1486756 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3396. Min Act: -0.1700
Data Index: 8630094 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3083. Min Act: -0.1700
Data Index: 4609915 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3396. Min Act: -0.1700
Data Index: 3382812 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3083. Min Act: -0.1700
Data Index: 5139909 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3083. Min Act: -0.1700
Data Index: 5015238 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3083. Min Act: -0.1700
Data Index: 6304156 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.2771. Min Act: -0.1700
Data Index: 3653156 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.2771. Min Act: -0.1700
Data Index: 3332436 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.2771. Min Act: -0.1700
Data Index: 2960723 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.2458. Min Act: -0.1700
Data Index: 3722704 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.3083. Min Act: -0.1700
Data Index: 7730921 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.2458. Min Act: -0.1700
Data Index: 3698447 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4958. Min Range: -5.4958
Max Act: 5.2146. Min Act: -0.1700
Data Index: 223093 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19