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

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

Neuron 253 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0003

Data Index: 119508 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0337. Min Act: -0.0003

Data Index: 860963 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0336. Min Act: -0.0003

Data Index: 645329 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0336. Min Act: -0.0003

Data Index: 831547 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0321. Min Act: -0.0003

Data Index: 64405 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0322. Min Act: -0.0003

Data Index: 989248 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0315. Min Act: -0.0004

Data Index: 574515 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0304. Min Act: -0.0002

Data Index: 282671 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1057804 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1295995 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0298. Min Act: -0.0004

Data Index: 168717 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0298. Min Act: -0.0002

Data Index: 97125 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0299. Min Act: -0.0003

Data Index: 116192 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0295. Min Act: -0.0003

Data Index: 29704 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0003

Data Index: 243400 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0293. Min Act: -0.0002

Data Index: 490633 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0003

Data Index: 193846 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1104649 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0003

Data Index: 633482 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1171379 (C4 (Web Text))

Max Activating Token Index: 180