Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1716 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.3207. Min Act: -0.1700
Data Index: 7238336 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.2582. Min Act: -0.1700
Data Index: 2607891 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5046848 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.1645. Min Act: -0.1700
Data Index: 7283056 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.1332. Min Act: -0.1700
Data Index: 7055251 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0707. Min Act: -0.1700
Data Index: 2607896 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0395. Min Act: -0.1700
Data Index: 7614775 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0395. Min Act: -0.1700
Data Index: 5285401 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0395. Min Act: -0.1700
Data Index: 2829720 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0395. Min Act: -0.1700
Data Index: 4623668 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0395. Min Act: -0.1700
Data Index: 4480617 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0082. Min Act: -0.1700
Data Index: 4928052 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0082. Min Act: -0.1700
Data Index: 1287471 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0082. Min Act: -0.1700
Data Index: 2311581 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3207. Min Range: -5.3207
Max Act: 4.9770. Min Act: -0.1700
Data Index: 133990 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3207. Min Range: -5.3207
Max Act: 4.9770. Min Act: -0.1700
Data Index: 4683767 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3207. Min Range: -5.3207
Max Act: 4.9770. Min Act: -0.1700
Data Index: 8821179 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3207. Min Range: -5.3207
Max Act: 5.0082. Min Act: -0.1700
Data Index: 3134628 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3207. Min Range: -5.3207
Max Act: 4.9770. Min Act: -0.1700
Data Index: 2594958 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3207. Min Range: -5.3207
Max Act: 4.9457. Min Act: -0.1700
Data Index: 3128708 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19