Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 464 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6729. Min Act: -0.1700
Data Index: 1232008 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.7354. Min Act: -0.1700
Data Index: 1160419 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6417. Min Act: -0.1700
Data Index: 675763 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.7042. Min Act: -0.1700
Data Index: 1055140 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6729. Min Act: -0.1700
Data Index: 190604 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6104. Min Act: -0.1700
Data Index: 847761 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6104. Min Act: -0.1700
Data Index: 687898 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.5479. Min Act: -0.1700
Data Index: 445602 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6104. Min Act: -0.1700
Data Index: 881076 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.5167. Min Act: -0.1700
Data Index: 157283 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6417. Min Act: -0.1700
Data Index: 547835 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.7042. Min Act: -0.1700
Data Index: 1250890 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.4229. Min Act: -0.1700
Data Index: 1029553 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.7042. Min Act: -0.1700
Data Index: 409336 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.5479. Min Act: -0.1700
Data Index: 713239 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.4854. Min Act: -0.1700
Data Index: 736506 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6104. Min Act: -0.1700
Data Index: 133668 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.5479. Min Act: -0.1700
Data Index: 280648 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.5479. Min Act: -0.1700
Data Index: 808362 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7354. Min Range: -4.7354
Max Act: 4.6104. Min Act: -0.1700
Data Index: 556923 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19