Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5944 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.9846. Min Act: -0.0000

Data Index: 1632428 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.7777. Min Act: -0.0000

Data Index: 1599480 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.7254. Min Act: -0.0000

Data Index: 12876 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.4421. Min Act: -0.0000

Data Index: 384756 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.5516. Min Act: -0.0000

Data Index: 1440473 (Python Code)

Max Activating Token Index: 677

Text #5

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.5266. Min Act: -0.0000

Data Index: 1441659 (Python Code)

Max Activating Token Index: 532

Text #6

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.5211. Min Act: -0.0000

Data Index: 993127 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.4969. Min Act: -0.0000

Data Index: 708364 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.6318. Min Act: -0.0000

Data Index: 883869 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.4734. Min Act: -0.0000

Data Index: 955271 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.6100. Min Act: -0.0000

Data Index: 1593301 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.3411. Min Act: -0.0000

Data Index: 1601183 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.4534. Min Act: -0.0000

Data Index: 1074249 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.3277. Min Act: -0.0000

Data Index: 1438548 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.5713. Min Act: -0.0000

Data Index: 1396446 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.3197. Min Act: -0.0000

Data Index: 1441706 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.5586. Min Act: -0.0000

Data Index: 1646237 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.4042. Min Act: -0.0000

Data Index: 839938 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.5403. Min Act: -0.0000

Data Index: 197866 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 2.9846. Min Range: -2.9846

Max Act: 2.3791. Min Act: -0.0000

Data Index: 1641636 (Python Code)

Max Activating Token Index: 130