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

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

Neuron 4709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1319217 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1739. Min Act: -0.0000

Data Index: 825822 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1519. Min Act: -0.0000

Data Index: 357091 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1433. Min Act: -0.0000

Data Index: 311427 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1405. Min Act: -0.0000

Data Index: 857012 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1318. Min Act: -0.0000

Data Index: 606183 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1325. Min Act: -0.0000

Data Index: 772278 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1346. Min Act: -0.0000

Data Index: 721064 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1130135 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1202. Min Act: -0.0000

Data Index: 805882 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1010. Min Act: -0.0000

Data Index: 226352 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1341315 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1160072 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1131. Min Act: -0.0000

Data Index: 320678 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1137. Min Act: -0.0000

Data Index: 259667 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1191. Min Act: -0.0000

Data Index: 266119 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1073. Min Act: -0.0000

Data Index: 378998 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1038. Min Act: -0.0000

Data Index: 415961 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1204. Min Act: -0.0000

Data Index: 183599 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1227. Min Act: -0.0000

Data Index: 201689 (C4 (Web Text))

Max Activating Token Index: 656