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

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

Neuron 3509 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.4272. Min Act: -0.0000

Data Index: 299549 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1349967 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.1023. Min Act: -0.0000

Data Index: 292056 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.1387. Min Act: -0.0000

Data Index: 852244 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1223559 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1102839 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0128. Min Act: -0.0000

Data Index: 478382 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0344. Min Act: -0.0000

Data Index: 727021 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.4272. Min Range: -1.4272

Max Act: 1.0182. Min Act: -0.0000

Data Index: 634379 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1303417 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9182. Min Act: -0.0000

Data Index: 374999 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8436. Min Act: -0.0000

Data Index: 959137 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8791. Min Act: -0.0000

Data Index: 386666 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.9656. Min Act: -0.0000

Data Index: 474372 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8452. Min Act: -0.0000

Data Index: 40285 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8103. Min Act: -0.0000

Data Index: 550276 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8645. Min Act: -0.0000

Data Index: 317836 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.7438. Min Act: -0.0000

Data Index: 174081 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.8059. Min Act: -0.0000

Data Index: 792480 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.4272. Min Range: -1.4272

Max Act: 0.7810. Min Act: -0.0000

Data Index: 227071 (C4 (Web Text))

Max Activating Token Index: 217