Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1809 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.6803. Min Act: -0.1700
Data Index: 3079912 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.3990. Min Act: -0.1700
Data Index: 5145063 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.2740. Min Act: -0.1700
Data Index: 296800 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.1178. Min Act: -0.1700
Data Index: 1928256 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.1178. Min Act: -0.1700
Data Index: 30246 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0865. Min Act: -0.1700
Data Index: 7076365 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0865. Min Act: -0.1700
Data Index: 7508868 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0865. Min Act: -0.1700
Data Index: 1648836 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0553. Min Act: -0.1700
Data Index: 2798659 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0865. Min Act: -0.1700
Data Index: 1563174 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0553. Min Act: -0.1700
Data Index: 8233690 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0553. Min Act: -0.1700
Data Index: 4858047 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0553. Min Act: -0.1700
Data Index: 4111382 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0553. Min Act: -0.1700
Data Index: 2255957 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6803. Min Range: -7.6803
Max Act: 7.0240. Min Act: -0.1700
Data Index: 4492033 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6803. Min Range: -7.6803
Max Act: 6.9928. Min Act: -0.1700
Data Index: 8669812 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6803. Min Range: -7.6803
Max Act: 6.9928. Min Act: -0.1700
Data Index: 7856552 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6803. Min Range: -7.6803
Max Act: 6.9615. Min Act: -0.1700
Data Index: 3291678 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6803. Min Range: -7.6803
Max Act: 6.9303. Min Act: -0.1700
Data Index: 8097025 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6803. Min Range: -7.6803
Max Act: 6.9303. Min Act: -0.1700
Data Index: 3282564 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19