Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2735 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2815. Min Act: -0.0000

Data Index: 505190 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2757. Min Act: -0.0001

Data Index: 963275 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2441. Min Act: -0.0001

Data Index: 10035 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1335294 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2449. Min Act: -0.0000

Data Index: 566487 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1245196 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2388. Min Act: -0.0001

Data Index: 528885 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2416. Min Act: -0.0000

Data Index: 619163 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2409. Min Act: -0.0000

Data Index: 144948 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2305. Min Act: -0.0000

Data Index: 945804 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2276. Min Act: -0.0000

Data Index: 488589 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1204717 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2274. Min Act: -0.0000

Data Index: 846383 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1352054 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2166. Min Act: -0.0000

Data Index: 3417 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2312. Min Act: -0.0000

Data Index: 717409 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2206. Min Act: -0.0001

Data Index: 445947 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2016. Min Act: -0.0000

Data Index: 263166 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2324. Min Act: -0.0001

Data Index: 751653 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2119. Min Act: -0.0000

Data Index: 904780 (C4 (Web Text))

Max Activating Token Index: 728