Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.3793. Min Act: -0.1700
Data Index: 2036282 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.3009. Min Act: -0.1700
Data Index: 4277983 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.2694. Min Act: -0.1700
Data Index: 5815704 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.2537. Min Act: -0.1700
Data Index: 4679204 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.2380. Min Act: -0.1700
Data Index: 2412417 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.2066. Min Act: -0.1700
Data Index: 1054110 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1909. Min Act: -0.1700
Data Index: 6004868 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1909. Min Act: -0.1700
Data Index: 2398654 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1751. Min Act: -0.1700
Data Index: 4770273 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1751. Min Act: -0.1700
Data Index: 752311 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1437. Min Act: -0.1700
Data Index: 6452858 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1594. Min Act: -0.1700
Data Index: 8426954 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1437. Min Act: -0.1700
Data Index: 1681388 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1594. Min Act: -0.1700
Data Index: 7310655 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1437. Min Act: -0.1700
Data Index: 6338888 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1279. Min Act: -0.1700
Data Index: 7948129 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1279. Min Act: -0.1700
Data Index: 6899341 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1122. Min Act: -0.1700
Data Index: 3372810 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1122. Min Act: -0.1700
Data Index: 6725363 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3793. Min Range: -3.3793
Max Act: 3.1122. Min Act: -0.1700
Data Index: 4677516 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19