Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.4451. Min Act: -0.1700
Data Index: 8722320 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.3201. Min Act: -0.1700
Data Index: 508077 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.2263. Min Act: -0.1700
Data Index: 1166385 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1951. Min Act: -0.1700
Data Index: 772665 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1951. Min Act: -0.1700
Data Index: 7198803 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1951. Min Act: -0.1700
Data Index: 2099978 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.2263. Min Act: -0.1700
Data Index: 6725163 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1638. Min Act: -0.1700
Data Index: 3485662 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1638. Min Act: -0.1700
Data Index: 6143467 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1951. Min Act: -0.1700
Data Index: 1480573 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1013. Min Act: -0.1700
Data Index: 4288707 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1013. Min Act: -0.1700
Data Index: 8273878 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.0701. Min Act: -0.1700
Data Index: 5945210 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1326. Min Act: -0.1700
Data Index: 6322745 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.1013. Min Act: -0.1700
Data Index: 1188008 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.0701. Min Act: -0.1700
Data Index: 4188522 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.0701. Min Act: -0.1700
Data Index: 7217641 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.0388. Min Act: -0.1700
Data Index: 7759726 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.0701. Min Act: -0.1700
Data Index: 2161382 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4451. Min Range: -5.4451
Max Act: 5.0388. Min Act: -0.1700
Data Index: 2023171 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19