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

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

Neuron 2133 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: 0.4228. Min Range: -0.4228

Max Act: 0.4228. Min Act: -0.0002

Data Index: 921193 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.4171. Min Act: -0.0001

Data Index: 888267 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3695. Min Act: -0.0001

Data Index: 353540 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3690. Min Act: -0.0001

Data Index: 1079531 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3903. Min Act: -0.0001

Data Index: 708860 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3225. Min Act: -0.0002

Data Index: 988566 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3531. Min Act: -0.0001

Data Index: 1291389 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3418. Min Act: -0.0001

Data Index: 365696 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3660. Min Act: -0.0001

Data Index: 367261 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1267175 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3376. Min Act: -0.0001

Data Index: 621623 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3206. Min Act: -0.0001

Data Index: 781705 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3272. Min Act: -0.0001

Data Index: 345573 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3476. Min Act: -0.0001

Data Index: 338502 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2951. Min Act: -0.0001

Data Index: 709524 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1258408 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3980. Min Act: -0.0001

Data Index: 921851 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2917. Min Act: -0.0001

Data Index: 623938 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.2917. Min Act: -0.0001

Data Index: 682910 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.4228. Min Range: -0.4228

Max Act: 0.3261. Min Act: -0.0001

Data Index: 626285 (C4 (Web Text))

Max Activating Token Index: 321