Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3457. Min Range: -6.3457
Max Act: 6.3457. Min Act: -0.1700
Data Index: 1733833 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3457. Min Range: -6.3457
Max Act: 6.2520. Min Act: -0.1700
Data Index: 517378 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3457. Min Range: -6.3457
Max Act: 6.1582. Min Act: -0.1700
Data Index: 943762 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3457. Min Range: -6.3457
Max Act: 6.0020. Min Act: -0.1700
Data Index: 8456189 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.9707. Min Act: -0.1700
Data Index: 2364511 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.9395. Min Act: -0.1700
Data Index: 6536635 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.9395. Min Act: -0.1700
Data Index: 1175507 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.9395. Min Act: -0.1700
Data Index: 8761615 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.9395. Min Act: -0.1700
Data Index: 4355250 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.8770. Min Act: -0.1700
Data Index: 1577249 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.9082. Min Act: -0.1700
Data Index: 4212447 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.8457. Min Act: -0.1700
Data Index: 5668373 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7832. Min Act: -0.1700
Data Index: 3388328 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7832. Min Act: -0.1700
Data Index: 8052197 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7520. Min Act: -0.1700
Data Index: 6799917 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7520. Min Act: -0.1700
Data Index: 4572369 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7520. Min Act: -0.1700
Data Index: 6057284 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7520. Min Act: -0.1700
Data Index: 1629300 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7520. Min Act: -0.1700
Data Index: 942296 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3457. Min Range: -6.3457
Max Act: 5.7207. Min Act: -0.1700
Data Index: 4313252 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19