Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 818 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.5413. Min Act: -0.1700
Data Index: 1478839 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.3538. Min Act: -0.1700
Data Index: 1360509 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.2913. Min Act: -0.1700
Data Index: 3177445 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.1663. Min Act: -0.1700
Data Index: 7644468 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.1663. Min Act: -0.1700
Data Index: 5949128 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.1663. Min Act: -0.1700
Data Index: 5220407 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.2288. Min Act: -0.1700
Data Index: 397002 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.1663. Min Act: -0.1700
Data Index: 1900267 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.1038. Min Act: -0.1700
Data Index: 2085157 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.1038. Min Act: -0.1700
Data Index: 3168307 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.0413. Min Act: -0.1700
Data Index: 8785892 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.0413. Min Act: -0.1700
Data Index: 2198991 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.0413. Min Act: -0.1700
Data Index: 3113783 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5413. Min Range: -8.5413
Max Act: 7.9788. Min Act: -0.1700
Data Index: 3852383 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5413. Min Range: -8.5413
Max Act: 8.0413. Min Act: -0.1700
Data Index: 3108891 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5413. Min Range: -8.5413
Max Act: 7.9788. Min Act: -0.1700
Data Index: 4430375 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5413. Min Range: -8.5413
Max Act: 7.9788. Min Act: -0.1700
Data Index: 324388 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5413. Min Range: -8.5413
Max Act: 7.9788. Min Act: -0.1700
Data Index: 2811873 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5413. Min Range: -8.5413
Max Act: 7.9788. Min Act: -0.1700
Data Index: 8112525 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5413. Min Range: -8.5413
Max Act: 7.9163. Min Act: -0.1700
Data Index: 2966070 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19