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

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

Neuron 3193 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3681. Min Act: -0.0000

Data Index: 542410 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.3494. Min Act: -0.0000

Data Index: 304491 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2738. Min Act: -0.0000

Data Index: 112479 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2843. Min Act: -0.0001

Data Index: 476323 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1267026 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1073572 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2691. Min Act: -0.0000

Data Index: 296598 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2545. Min Act: -0.0000

Data Index: 18266 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2490. Min Act: 0.0000

Data Index: 406676 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2398. Min Act: 0.0000

Data Index: 581092 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2299. Min Act: -0.0000

Data Index: 373793 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2388. Min Act: -0.0000

Data Index: 312909 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2395. Min Act: -0.0000

Data Index: 919151 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2367. Min Act: -0.0000

Data Index: 30923 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1007386 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1288181 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2199. Min Act: -0.0001

Data Index: 830669 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2258. Min Act: -0.0000

Data Index: 830008 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2226. Min Act: -0.0000

Data Index: 231531 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.3681. Min Range: -0.3681

Max Act: 0.2366. Min Act: -0.0001

Data Index: 635329 (C4 (Web Text))

Max Activating Token Index: 642