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

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

Neuron 2076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2947. Min Act: -0.0001

Data Index: 500930 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2986. Min Act: -0.0001

Data Index: 1185001 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2863. Min Act: -0.0001

Data Index: 1280646 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1466296 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2713. Min Act: -0.0001

Data Index: 344118 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1311996 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2499. Min Act: -0.0001

Data Index: 1397373 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1030655 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1565659 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2428. Min Act: -0.0001

Data Index: 230864 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1565903 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2405. Min Act: -0.0001

Data Index: 869139 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2375. Min Act: -0.0001

Data Index: 1637898 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1304895 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1506248 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2391. Min Act: -0.0001

Data Index: 658222 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2166. Min Act: -0.0001

Data Index: 957518 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1295586 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1488043 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.2986. Min Range: -0.2986

Max Act: 0.2220. Min Act: -0.0001

Data Index: 1445618 (Python Code)

Max Activating Token Index: 74