Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2249. Min Range: -4.2249
Max Act: 4.2249. Min Act: -0.1700
Data Index: 4478495 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2249. Min Range: -4.2249
Max Act: 4.1311. Min Act: -0.1700
Data Index: 3434468 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2249. Min Range: -4.2249
Max Act: 4.0999. Min Act: -0.1700
Data Index: 4221353 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2249. Min Range: -4.2249
Max Act: 4.0686. Min Act: -0.1700
Data Index: 2658741 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2249. Min Range: -4.2249
Max Act: 4.0374. Min Act: -0.1700
Data Index: 8011285 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2249. Min Range: -4.2249
Max Act: 4.0061. Min Act: -0.1700
Data Index: 8659873 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9749. Min Act: -0.1700
Data Index: 8727369 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9436. Min Act: -0.1700
Data Index: 8223714 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9436. Min Act: -0.1700
Data Index: 1322539 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9123. Min Act: -0.1700
Data Index: 3320021 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9436. Min Act: -0.1700
Data Index: 4334561 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9123. Min Act: -0.1700
Data Index: 8452498 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9123. Min Act: -0.1700
Data Index: 949553 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.8811. Min Act: -0.1700
Data Index: 4502327 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.8811. Min Act: -0.1700
Data Index: 4395996 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.8811. Min Act: -0.1700
Data Index: 4283699 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.8811. Min Act: -0.1700
Data Index: 4255266 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.8811. Min Act: -0.1700
Data Index: 3898595 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.8811. Min Act: -0.1700
Data Index: 2363463 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2249. Min Range: -4.2249
Max Act: 3.9123. Min Act: -0.1700
Data Index: 2253911 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19