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

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

Neuron 1165 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: 0.2406. Min Range: -0.2406

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1083030 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2206. Min Act: -0.0001

Data Index: 157210 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2314. Min Act: -0.0001

Data Index: 460057 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2382. Min Act: -0.0001

Data Index: 8948 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0001

Data Index: 207299 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2019. Min Act: -0.0001

Data Index: 942326 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2335. Min Act: -0.0001

Data Index: 273284 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2089. Min Act: -0.0001

Data Index: 911334 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2365. Min Act: -0.0001

Data Index: 853322 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2114. Min Act: -0.0001

Data Index: 230724 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2140. Min Act: -0.0001

Data Index: 403618 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2034. Min Act: -0.0001

Data Index: 76860 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2020. Min Act: -0.0001

Data Index: 560939 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2012. Min Act: -0.0001

Data Index: 55944 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1802. Min Act: -0.0001

Data Index: 821804 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1872. Min Act: -0.0001

Data Index: 995218 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2160. Min Act: -0.0001

Data Index: 518281 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1978. Min Act: -0.0001

Data Index: 997850 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1961. Min Act: -0.0001

Data Index: 872796 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1952. Min Act: -0.0001

Data Index: 752992 (C4 (Web Text))

Max Activating Token Index: 830