Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1299 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0413. Min Range: -7.0413
Max Act: 7.0413. Min Act: -0.1700
Data Index: 5533601 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.9163. Min Act: -0.1700
Data Index: 744822 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.8538. Min Act: -0.1700
Data Index: 850505 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.8226. Min Act: -0.1700
Data Index: 7091267 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.8226. Min Act: -0.1700
Data Index: 6800345 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.7913. Min Act: -0.1700
Data Index: 5299005 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.7288. Min Act: -0.1700
Data Index: 2196440 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.7601. Min Act: -0.1700
Data Index: 5136574 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.6976. Min Act: -0.1700
Data Index: 7860555 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.6976. Min Act: -0.1700
Data Index: 2454830 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.6663. Min Act: -0.1700
Data Index: 8043271 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.6038. Min Act: -0.1700
Data Index: 7853149 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 7126079 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 5512816 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 1003767 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 1812397 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 3857069 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 3097948 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5726. Min Act: -0.1700
Data Index: 4978079 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0413. Min Range: -7.0413
Max Act: 6.5413. Min Act: -0.1700
Data Index: 7146410 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19