Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3099 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1081290 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2349. Min Act: -0.0001

Data Index: 275501 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2373. Min Act: -0.0001

Data Index: 761505 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1312717 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2316. Min Act: -0.0001

Data Index: 1200475 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2172. Min Act: -0.0001

Data Index: 181665 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2213. Min Act: -0.0001

Data Index: 253627 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2180. Min Act: -0.0001

Data Index: 772537 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1223502 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2142. Min Act: -0.0001

Data Index: 95921 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2177. Min Act: -0.0001

Data Index: 469595 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2063. Min Act: -0.0001

Data Index: 498282 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1026216 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1180941 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2123. Min Act: -0.0001

Data Index: 879583 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1971. Min Act: -0.0001

Data Index: 560318 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.1972. Min Act: -0.0001

Data Index: 740656 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2132. Min Act: -0.0001

Data Index: 344154 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2008. Min Act: -0.0001

Data Index: 905528 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.2473. Min Range: -0.2473

Max Act: 0.2008. Min Act: -0.0001

Data Index: 640709 (C4 (Web Text))

Max Activating Token Index: 382