Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 556 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.6387. Min Act: -0.1700
Data Index: 255625 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.5450. Min Act: -0.1700
Data Index: 8167429 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.4200. Min Act: -0.1700
Data Index: 5112132 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.4200. Min Act: -0.1700
Data Index: 6767625 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.4512. Min Act: -0.1700
Data Index: 241702 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.4200. Min Act: -0.1700
Data Index: 8463443 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3575. Min Act: -0.1700
Data Index: 235518 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3575. Min Act: -0.1700
Data Index: 5435580 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3575. Min Act: -0.1700
Data Index: 1084329 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2950. Min Act: -0.1700
Data Index: 1077120 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.3262. Min Act: -0.1700
Data Index: 4460931 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2637. Min Act: -0.1700
Data Index: 3820786 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2637. Min Act: -0.1700
Data Index: 5172756 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2325. Min Act: -0.1700
Data Index: 7444006 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2012. Min Act: -0.1700
Data Index: 6259153 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2325. Min Act: -0.1700
Data Index: 1481450 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.2012. Min Act: -0.1700
Data Index: 1695246 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.1700. Min Act: -0.1700
Data Index: 7386261 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.1700. Min Act: -0.1700
Data Index: 14187 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6387. Min Range: -6.6387
Max Act: 6.1387. Min Act: -0.1700
Data Index: 2722519 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19