Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4193 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.2455. Min Act: -0.0000

Data Index: 397006 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1193566 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.0145. Min Act: -0.0000

Data Index: 88102 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9267. Min Act: -0.0000

Data Index: 525474 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9334. Min Act: -0.0000

Data Index: 115613 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8964. Min Act: 0.0000

Data Index: 597756 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8580. Min Act: -0.0000

Data Index: 832863 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7905. Min Act: -0.0000

Data Index: 981533 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1250908 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8624. Min Act: -0.0000

Data Index: 159990 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8457. Min Act: -0.0000

Data Index: 310286 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8440. Min Act: -0.0000

Data Index: 796347 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7621. Min Act: -0.0000

Data Index: 535942 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7758. Min Act: -0.0000

Data Index: 999578 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1036775 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1094045 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7484. Min Act: -0.0000

Data Index: 514370 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8089. Min Act: -0.0000

Data Index: 473057 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7975. Min Act: -0.0000

Data Index: 85925 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8270. Min Act: -0.0000

Data Index: 788040 (C4 (Web Text))

Max Activating Token Index: 207