Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 354 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0358. Min Act: -0.0001

Data Index: 462219 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0001

Data Index: 644053 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0361. Min Act: -0.0001

Data Index: 324248 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0342. Min Act: -0.0001

Data Index: 352557 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0341. Min Act: -0.0001

Data Index: 367638 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0331. Min Act: -0.0001

Data Index: 470439 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0325. Min Act: -0.0001

Data Index: 938915 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0319. Min Act: -0.0001

Data Index: 371299 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0322. Min Act: -0.0001

Data Index: 495772 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0304. Min Act: -0.0001

Data Index: 308248 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0298. Min Act: -0.0001

Data Index: 709592 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1549753 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0278. Min Act: -0.0001

Data Index: 278247 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0001

Data Index: 993204 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1272943 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0297. Min Act: -0.0001

Data Index: 424923 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0307. Min Act: -0.0001

Data Index: 973350 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0282. Min Act: -0.0001

Data Index: 249869 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0307. Min Act: -0.0001

Data Index: 182192 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1063104 (C4 (Web Text))

Max Activating Token Index: 974