Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 143 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0449. Min Act: -0.0006

Data Index: 418504 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0006

Data Index: 164954 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0410. Min Act: -0.0006

Data Index: 22153 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0378. Min Act: -0.0006

Data Index: 611382 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1339526 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1337414 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1198474 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0405. Min Act: -0.0006

Data Index: 576981 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0335. Min Act: -0.0006

Data Index: 378738 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0365. Min Act: -0.0006

Data Index: 726360 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0395. Min Act: -0.0006

Data Index: 1252415 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1213893 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0391. Min Act: -0.0006

Data Index: 493901 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0383. Min Act: -0.0006

Data Index: 683189 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0381. Min Act: -0.0006

Data Index: 221311 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1270566 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0360. Min Act: -0.0006

Data Index: 1182630 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0376. Min Act: -0.0006

Data Index: 568757 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1254413 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1181160 (C4 (Web Text))

Max Activating Token Index: 415