Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2301 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2667. Min Act: -0.0001

Data Index: 578435 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.3061. Min Act: -0.0001

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2867. Min Act: -0.0001

Data Index: 17514 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2616. Min Act: -0.0001

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2527. Min Act: -0.0001

Data Index: 604141 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2491. Min Act: -0.0001

Data Index: 1273933 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2164. Min Act: -0.0001

Data Index: 347754 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2503. Min Act: -0.0001

Data Index: 590527 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2440. Min Act: -0.0001

Data Index: 520928 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2091. Min Act: -0.0001

Data Index: 92594 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1286273 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2224. Min Act: -0.0001

Data Index: 406665 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1080026 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1172941 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2200. Min Act: -0.0001

Data Index: 523870 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1142891 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2044. Min Act: -0.0001

Data Index: 135374 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.1982. Min Act: -0.0001

Data Index: 532630 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1203290 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.3061. Min Range: -0.3061

Max Act: 0.2099. Min Act: -0.0001

Data Index: 361711 (C4 (Web Text))

Max Activating Token Index: 516