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

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

Neuron 3 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1197794 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1261846 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1200577 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0351. Min Act: -0.0003

Data Index: 197688 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0344. Min Act: -0.0003

Data Index: 621379 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0336. Min Act: -0.0003

Data Index: 11741 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1257736 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0325. Min Act: -0.0003

Data Index: 21433 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1135470 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1110855 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0318. Min Act: -0.0003

Data Index: 3425 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1132537 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0318. Min Act: -0.0003

Data Index: 988068 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0330. Min Act: -0.0003

Data Index: 621559 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0315. Min Act: -0.0003

Data Index: 439558 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1196888 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0293. Min Act: -0.0003

Data Index: 649062 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1079054 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0309. Min Act: -0.0003

Data Index: 852507 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0326. Min Act: -0.0003

Data Index: 316196 (C4 (Web Text))

Max Activating Token Index: 865