Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4216 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3603. Min Act: -0.0001

Data Index: 447228 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.5259. Min Act: -0.0001

Data Index: 526443 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.1439. Min Act: -0.0001

Data Index: 1219789 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.4352. Min Act: -0.0001

Data Index: 99977 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.2528. Min Act: -0.0001

Data Index: 573889 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.2402. Min Act: -0.0001

Data Index: 762783 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3870. Min Act: -0.0001

Data Index: 385660 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.2839. Min Act: -0.0001

Data Index: 1337682 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.2730. Min Act: -0.0001

Data Index: 263667 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.2772. Min Act: -0.0001

Data Index: 1154234 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3740. Min Act: -0.0001

Data Index: 422365 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.3215. Min Act: -0.0001

Data Index: 237907 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.0241. Min Act: -0.0001

Data Index: 386192 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.1383. Min Act: -0.0001

Data Index: 189653 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.1507. Min Act: -0.0001

Data Index: 639651 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.1191. Min Act: -0.0001

Data Index: 1078932 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.5259. Min Range: -3.5259

Max Act: 2.9483. Min Act: -0.0001

Data Index: 952218 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.0892. Min Act: -0.0001

Data Index: 1148809 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 3.5259. Min Range: -3.5259

Max Act: 3.0366. Min Act: -0.0001

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 3.5259. Min Range: -3.5259

Max Act: 2.9167. Min Act: -0.0001

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 353