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

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

Neuron 2963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.3074. Min Act: -0.0000

Data Index: 434388 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2535. Min Act: -0.0001

Data Index: 38257 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2349. Min Act: -0.0001

Data Index: 873380 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2309. Min Act: -0.0000

Data Index: 376867 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2352. Min Act: -0.0001

Data Index: 880228 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2975. Min Act: -0.0000

Data Index: 156243 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2301. Min Act: -0.0000

Data Index: 861969 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2475. Min Act: -0.0000

Data Index: 503533 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2060. Min Act: -0.0000

Data Index: 921249 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2451. Min Act: -0.0000

Data Index: 398502 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2064. Min Act: -0.0001

Data Index: 286792 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2204. Min Act: -0.0001

Data Index: 1366410 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1325995 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2197. Min Act: -0.0000

Data Index: 27039 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.2102. Min Act: -0.0001

Data Index: 724858 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1717. Min Act: -0.0000

Data Index: 503115 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1008415 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1582. Min Act: -0.0000

Data Index: 115954 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1303649 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.3074. Min Range: -0.3074

Max Act: 0.1712. Min Act: -0.0001

Data Index: 983546 (C4 (Web Text))

Max Activating Token Index: 984