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

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

Neuron 3982 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4431. Min Range: -5.4431

Max Act: 5.4431. Min Act: -0.0001

Data Index: 1237337 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.8046. Min Act: -0.0001

Data Index: 579912 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.9302. Min Act: -0.0001

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.5044. Min Act: -0.0001

Data Index: 288160 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.4276. Min Act: -0.0001

Data Index: 961243 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.5639. Min Act: -0.0001

Data Index: 1012451 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.2429. Min Act: -0.0001

Data Index: 1227391 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.5574. Min Act: -0.0001

Data Index: 121636 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.5638. Min Act: -0.0001

Data Index: 954046 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.1728. Min Act: -0.0001

Data Index: 1035313 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.1289. Min Act: -0.0001

Data Index: 165551 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.2271. Min Act: -0.0001

Data Index: 727136 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.0396. Min Act: -0.0001

Data Index: 353270 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 5.4431. Min Range: -5.4431

Max Act: 3.8352. Min Act: -0.0001

Data Index: 368147 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.1240. Min Act: -0.0001

Data Index: 1027431 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.4216. Min Act: -0.0001

Data Index: 776936 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.2527. Min Act: -0.0001

Data Index: 1319056 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.2513. Min Act: -0.0001

Data Index: 601187 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.2168. Min Act: -0.0001

Data Index: 1285216 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 5.4431. Min Range: -5.4431

Max Act: 4.0358. Min Act: -0.0001

Data Index: 823033 (C4 (Web Text))

Max Activating Token Index: 201