Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2694 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1046146 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2639. Min Act: -0.0001

Data Index: 960614 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1016901 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2527. Min Act: -0.0001

Data Index: 121485 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2564. Min Act: -0.0001

Data Index: 225887 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2372. Min Act: -0.0001

Data Index: 760498 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2333. Min Act: -0.0001

Data Index: 1017599 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2332. Min Act: -0.0001

Data Index: 216106 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1231461 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2356. Min Act: -0.0001

Data Index: 277427 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2195. Min Act: -0.0001

Data Index: 353260 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2164. Min Act: -0.0001

Data Index: 399718 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2193. Min Act: -0.0001

Data Index: 1001567 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.1947. Min Act: -0.0001

Data Index: 392748 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2232. Min Act: -0.0001

Data Index: 735933 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1138243 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2051. Min Act: -0.0001

Data Index: 178423 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2132. Min Act: -0.0001

Data Index: 141173 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2244. Min Act: -0.0001

Data Index: 859254 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.3538. Min Range: -0.3538

Max Act: 0.2152. Min Act: -0.0001

Data Index: 293475 (C4 (Web Text))

Max Activating Token Index: 955