Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2271. Min Range: -4.2271

Max Act: 4.2271. Min Act: -0.0000

Data Index: 998843 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.6443. Min Act: -0.0001

Data Index: 600539 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.2453. Min Act: -0.0001

Data Index: 1045637 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.2141. Min Act: -0.0000

Data Index: 1053241 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.4519. Min Act: -0.0001

Data Index: 390234 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.3060. Min Act: -0.0001

Data Index: 724558 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.7865. Min Act: -0.0001

Data Index: 483269 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.0576. Min Act: -0.0000

Data Index: 819012 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.2261. Min Act: -0.0001

Data Index: 514858 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.1319. Min Act: -0.0000

Data Index: 261951 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.8407. Min Act: -0.0001

Data Index: 250619 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.2638. Min Act: -0.0000

Data Index: 155037 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.9220. Min Act: -0.0001

Data Index: 662124 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.0295. Min Act: -0.0001

Data Index: 1205477 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.9297. Min Act: -0.0001

Data Index: 1057295 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.8364. Min Act: -0.0001

Data Index: 224872 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.4397. Min Act: -0.0000

Data Index: 61172 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.0288. Min Act: -0.0001

Data Index: 482875 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 4.2271. Min Range: -4.2271

Max Act: 3.2184. Min Act: -0.0000

Data Index: 871352 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 4.2271. Min Range: -4.2271

Max Act: 2.7331. Min Act: -0.0001

Data Index: 1306402 (C4 (Web Text))

Max Activating Token Index: 560