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

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

Neuron 4053 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: 0.2817. Min Range: -0.2817

Max Act: 0.2817. Min Act: -0.0001

Data Index: 392693 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1621002 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2729. Min Act: -0.0001

Data Index: 36176 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2518. Min Act: -0.0001

Data Index: 49534 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1543043 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2535. Min Act: -0.0001

Data Index: 388015 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1596191 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1596100 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1379007 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1386744 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1491700 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2405. Min Act: -0.0001

Data Index: 767179 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2419. Min Act: -0.0001

Data Index: 560230 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2309. Min Act: -0.0001

Data Index: 1362490 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2184. Min Act: -0.0001

Data Index: 165325 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2247. Min Act: -0.0001

Data Index: 1656700 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2313. Min Act: -0.0001

Data Index: 1524982 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2317. Min Act: -0.0001

Data Index: 1610530 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1577499 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.2817. Min Range: -0.2817

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1588933 (Python Code)

Max Activating Token Index: 59