Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1367 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.5907. Min Act: -0.1700
Data Index: 8704311 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.5595. Min Act: -0.1700
Data Index: 2582033 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.5907. Min Act: -0.1700
Data Index: 4886469 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.5282. Min Act: -0.1700
Data Index: 6246775 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.4970. Min Act: -0.1700
Data Index: 6138337 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.4657. Min Act: -0.1700
Data Index: 8052336 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.4032. Min Act: -0.1700
Data Index: 275869 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.4032. Min Act: -0.1700
Data Index: 1641313 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3720. Min Act: -0.1700
Data Index: 2819808 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3720. Min Act: -0.1700
Data Index: 2196479 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3720. Min Act: -0.1700
Data Index: 4493294 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3407. Min Act: -0.1700
Data Index: 3956148 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1679356 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3407. Min Act: -0.1700
Data Index: 4544140 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3407. Min Act: -0.1700
Data Index: 5349319 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3095. Min Act: -0.1700
Data Index: 7189539 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3095. Min Act: -0.1700
Data Index: 1541844 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.3095. Min Act: -0.1700
Data Index: 8123830 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.2782. Min Act: -0.1700
Data Index: 8494807 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5907. Min Range: -6.5907
Max Act: 6.2782. Min Act: -0.1700
Data Index: 6765992 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19