Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5849 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2522. Min Act: -0.0001

Data Index: 831023 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2195. Min Act: -0.0001

Data Index: 739339 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2185. Min Act: -0.0001

Data Index: 8405 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2288. Min Act: -0.0001

Data Index: 214785 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1329948 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1219093 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2351. Min Act: -0.0001

Data Index: 144720 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.1965. Min Act: -0.0001

Data Index: 692517 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2199. Min Act: -0.0001

Data Index: 1029204 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1250424 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2067. Min Act: -0.0001

Data Index: 99274 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.1853. Min Act: -0.0001

Data Index: 973817 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2106. Min Act: -0.0001

Data Index: 285672 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2106. Min Act: -0.0001

Data Index: 242112 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2143. Min Act: -0.0001

Data Index: 761382 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2158. Min Act: -0.0001

Data Index: 633475 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2228. Min Act: -0.0001

Data Index: 628549 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2124. Min Act: -0.0001

Data Index: 830289 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2120. Min Act: -0.0001

Data Index: 411403 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.2522. Min Range: -0.2522

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1228717 (C4 (Web Text))

Max Activating Token Index: 236