Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1204 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2944. Min Act: -0.0002

Data Index: 218567 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2630. Min Act: -0.0002

Data Index: 286474 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2683. Min Act: -0.0002

Data Index: 532975 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2638. Min Act: -0.0002

Data Index: 241815 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2417. Min Act: -0.0002

Data Index: 693583 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2274. Min Act: -0.0002

Data Index: 237979 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2412. Min Act: -0.0002

Data Index: 542460 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2407. Min Act: -0.0002

Data Index: 1165333 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2370. Min Act: -0.0002

Data Index: 1303190 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2263. Min Act: -0.0002

Data Index: 1121871 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2196. Min Act: -0.0002

Data Index: 453793 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2279. Min Act: -0.0002

Data Index: 231273 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2319. Min Act: -0.0002

Data Index: 575766 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2231. Min Act: -0.0002

Data Index: 663163 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2147. Min Act: -0.0002

Data Index: 980070 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2190. Min Act: -0.0002

Data Index: 11915 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2204. Min Act: -0.0002

Data Index: 483046 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2061. Min Act: -0.0002

Data Index: 281441 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2132. Min Act: -0.0002

Data Index: 888342 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.2944. Min Range: -0.2944

Max Act: 0.2223. Min Act: -0.0002

Data Index: 1353984 (C4 (Web Text))

Max Activating Token Index: 363