Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4576 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.3221. Min Act: -0.1700
Data Index: 5823901 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.2284. Min Act: -0.1700
Data Index: 2819832 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.1346. Min Act: -0.1700
Data Index: 7413545 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0721. Min Act: -0.1700
Data Index: 8606536 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0721. Min Act: -0.1700
Data Index: 7874402 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0721. Min Act: -0.1700
Data Index: 3834204 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0721. Min Act: -0.1700
Data Index: 1275674 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0721. Min Act: -0.1700
Data Index: 5523675 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0721. Min Act: -0.1700
Data Index: 2015607 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0409. Min Act: -0.1700
Data Index: 2290155 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0096. Min Act: -0.1700
Data Index: 941268 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0096. Min Act: -0.1700
Data Index: 8083472 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0096. Min Act: -0.1700
Data Index: 71895 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3221. Min Range: -5.3221
Max Act: 5.0096. Min Act: -0.1700
Data Index: 5990407 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3221. Min Range: -5.3221
Max Act: 4.9784. Min Act: -0.1700
Data Index: 1929941 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3221. Min Range: -5.3221
Max Act: 4.9471. Min Act: -0.1700
Data Index: 6470305 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3221. Min Range: -5.3221
Max Act: 4.9471. Min Act: -0.1700
Data Index: 1582431 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3221. Min Range: -5.3221
Max Act: 4.9784. Min Act: -0.1700
Data Index: 8329986 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3221. Min Range: -5.3221
Max Act: 4.9471. Min Act: -0.1700
Data Index: 1309710 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3221. Min Range: -5.3221
Max Act: 4.8846. Min Act: -0.1700
Data Index: 2060679 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19