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

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

Neuron 4394 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0002

Data Index: 781074 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0495. Min Act: -0.0002

Data Index: 967893 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0441. Min Act: -0.0002

Data Index: 105351 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0336. Min Act: -0.0002

Data Index: 933164 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0408. Min Act: -0.0002

Data Index: 406177 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0388. Min Act: -0.0002

Data Index: 97529 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0399. Min Act: -0.0002

Data Index: 438095 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1154567 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0365. Min Act: -0.0002

Data Index: 716663 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0345. Min Act: -0.0002

Data Index: 801888 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0337. Min Act: -0.0002

Data Index: 107473 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1085216 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0331. Min Act: -0.0002

Data Index: 192655 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0382. Min Act: -0.0002

Data Index: 566252 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1079917 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0340. Min Act: -0.0002

Data Index: 622324 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0301. Min Act: -0.0002

Data Index: 456465 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1013956 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1061410 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0329. Min Act: -0.0002

Data Index: 374670 (C4 (Web Text))

Max Activating Token Index: 637