Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1136 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1217572 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0330. Min Act: -0.0004

Data Index: 837074 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0320. Min Act: -0.0003

Data Index: 385536 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1042480 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0311. Min Act: -0.0004

Data Index: 717103 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1125413 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0316. Min Act: -0.0003

Data Index: 854906 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0302. Min Act: -0.0003

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0347. Min Act: -0.0003

Data Index: 506471 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0300. Min Act: -0.0003

Data Index: 848897 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0308. Min Act: -0.0004

Data Index: 97201 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0316. Min Act: -0.0004

Data Index: 439302 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0303. Min Act: -0.0004

Data Index: 1180090 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0307. Min Act: -0.0004

Data Index: 103465 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0306. Min Act: -0.0003

Data Index: 956792 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1349302 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0299. Min Act: -0.0004

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1032894 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1072119 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0297. Min Act: -0.0004

Data Index: 494710 (C4 (Web Text))

Max Activating Token Index: 230