Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.2777. Min Act: -0.1700
Data Index: 8551633 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.2464. Min Act: -0.1700
Data Index: 2636358 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.2152. Min Act: -0.1700
Data Index: 945675 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.2464. Min Act: -0.1700
Data Index: 6694607 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.2152. Min Act: -0.1700
Data Index: 6694609 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1839. Min Act: -0.1700
Data Index: 4627176 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1839. Min Act: -0.1700
Data Index: 4303121 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1839. Min Act: -0.1700
Data Index: 5460972 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1839. Min Act: -0.1700
Data Index: 8119749 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1839. Min Act: -0.1700
Data Index: 6694608 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1527. Min Act: -0.1700
Data Index: 5608075 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1527. Min Act: -0.1700
Data Index: 5869377 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1527. Min Act: -0.1700
Data Index: 7068106 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1527. Min Act: -0.1700
Data Index: 6103980 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.0902. Min Act: -0.1700
Data Index: 4442141 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1214. Min Act: -0.1700
Data Index: 8121054 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1214. Min Act: -0.1700
Data Index: 7296330 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1279267 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6926654 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2777. Min Range: -6.2777
Max Act: 6.1214. Min Act: -0.1700
Data Index: 4671978 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19