Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5929 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0878. Min Range: -5.0878
Max Act: 5.0878. Min Act: -0.1700
Data Index: 4118503 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0878. Min Range: -5.0878
Max Act: 5.0566. Min Act: -0.1700
Data Index: 6753397 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0878. Min Range: -5.0878
Max Act: 5.0253. Min Act: -0.1700
Data Index: 1118681 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.9941. Min Act: -0.1700
Data Index: 1878787 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.9316. Min Act: -0.1700
Data Index: 4139226 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.9003. Min Act: -0.1700
Data Index: 278969 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.8066. Min Act: -0.1700
Data Index: 4342894 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.8378. Min Act: -0.1700
Data Index: 7799207 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.8378. Min Act: -0.1700
Data Index: 352557 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.7441. Min Act: -0.1700
Data Index: 8532597 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.7128. Min Act: -0.1700
Data Index: 8135586 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.7128. Min Act: -0.1700
Data Index: 6306170 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.7128. Min Act: -0.1700
Data Index: 702109 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.7128. Min Act: -0.1700
Data Index: 620551 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.6816. Min Act: -0.1700
Data Index: 4366447 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.6191. Min Act: -0.1700
Data Index: 3409446 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.6503. Min Act: -0.1700
Data Index: 5359726 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.5878. Min Act: -0.1700
Data Index: 6668360 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.6191. Min Act: -0.1700
Data Index: 5675413 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0878. Min Range: -5.0878
Max Act: 4.5878. Min Act: -0.1700
Data Index: 7827486 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19