Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1409. Min Range: -5.1409
Max Act: 5.1409. Min Act: -0.1700
Data Index: 4801201 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1409. Min Range: -5.1409
Max Act: 5.1097. Min Act: -0.1700
Data Index: 4888092 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1409. Min Range: -5.1409
Max Act: 5.0472. Min Act: -0.1700
Data Index: 600018 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.9534. Min Act: -0.1700
Data Index: 3579332 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.9534. Min Act: -0.1700
Data Index: 2691551 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.9534. Min Act: -0.1700
Data Index: 6832822 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.9534. Min Act: -0.1700
Data Index: 3998163 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.9534. Min Act: -0.1700
Data Index: 2102283 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.9222. Min Act: -0.1700
Data Index: 4308876 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8909. Min Act: -0.1700
Data Index: 6861370 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8909. Min Act: -0.1700
Data Index: 751637 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8909. Min Act: -0.1700
Data Index: 2432289 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8284. Min Act: -0.1700
Data Index: 926112 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8597. Min Act: -0.1700
Data Index: 5494207 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8284. Min Act: -0.1700
Data Index: 6563238 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8284. Min Act: -0.1700
Data Index: 7943011 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8284. Min Act: -0.1700
Data Index: 5815108 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8597. Min Act: -0.1700
Data Index: 6479408 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3509949 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1409. Min Range: -5.1409
Max Act: 4.8284. Min Act: -0.1700
Data Index: 422793 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19