Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1990 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1323289 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0397. Min Act: -0.0001

Data Index: 353288 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0381. Min Act: -0.0001

Data Index: 127900 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1449659 (Python Code)

Max Activating Token Index: 714

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0350. Min Act: -0.0000

Data Index: 474463 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1510111 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0298. Min Act: -0.0001

Data Index: 132030 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1641806 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1394742 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1198045 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1500348 (Python Code)

Max Activating Token Index: 901

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1055981 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0314. Min Act: -0.0001

Data Index: 790551 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0312. Min Act: -0.0001

Data Index: 438135 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1557318 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0343. Min Act: -0.0000

Data Index: 919214 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0323. Min Act: -0.0000

Data Index: 856202 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0297. Min Act: -0.0001

Data Index: 450468 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0331. Min Act: -0.0001

Data Index: 317142 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0338. Min Act: -0.0001

Data Index: 6186 (C4 (Web Text))

Max Activating Token Index: 528