Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2389. Min Range: -6.2389
Max Act: 6.2389. Min Act: -0.1700
Data Index: 4577818 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2389. Min Range: -6.2389
Max Act: 6.0514. Min Act: -0.1700
Data Index: 532274 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2389. Min Range: -6.2389
Max Act: 6.0202. Min Act: -0.1700
Data Index: 652239 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.9264. Min Act: -0.1700
Data Index: 3769306 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.9264. Min Act: -0.1700
Data Index: 6995302 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.8327. Min Act: -0.1700
Data Index: 3964336 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7702. Min Act: -0.1700
Data Index: 7177911 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7389. Min Act: -0.1700
Data Index: 7109918 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7389. Min Act: -0.1700
Data Index: 4818474 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7389. Min Act: -0.1700
Data Index: 1910286 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6764. Min Act: -0.1700
Data Index: 4353353 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.7077. Min Act: -0.1700
Data Index: 1774498 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6764. Min Act: -0.1700
Data Index: 6304562 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6452. Min Act: -0.1700
Data Index: 904048 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6139. Min Act: -0.1700
Data Index: 2958170 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6452. Min Act: -0.1700
Data Index: 780718 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6139. Min Act: -0.1700
Data Index: 2854702 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6139. Min Act: -0.1700
Data Index: 2126166 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6139. Min Act: -0.1700
Data Index: 2265300 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2389. Min Range: -6.2389
Max Act: 5.6139. Min Act: -0.1700
Data Index: 1083738 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19