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

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

Neuron 630 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: 1.7497. Min Range: -1.7497

Max Act: 1.7497. Min Act: -0.0001

Data Index: 808520 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.5618. Min Act: -0.0001

Data Index: 892236 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.5226. Min Act: -0.0001

Data Index: 1293344 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.1253. Min Act: -0.0001

Data Index: 1357336 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2066. Min Act: -0.0001

Data Index: 1331882 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.3132. Min Act: -0.0001

Data Index: 87688 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.4300. Min Act: -0.0001

Data Index: 920142 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.4228. Min Act: -0.0001

Data Index: 475220 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.0324. Min Act: -0.0001

Data Index: 273413 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.4163. Min Act: -0.0001

Data Index: 1101121 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2488. Min Act: -0.0001

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.3422. Min Act: -0.0001

Data Index: 220644 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.1035. Min Act: -0.0001

Data Index: 1224893 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.6683. Min Act: -0.0001

Data Index: 1256686 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2977. Min Act: -0.0001

Data Index: 1057316 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2922. Min Act: -0.0001

Data Index: 461633 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2206. Min Act: -0.0001

Data Index: 691696 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2427. Min Act: -0.0001

Data Index: 431049 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2152. Min Act: -0.0001

Data Index: 458049 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.7497. Min Range: -1.7497

Max Act: 1.2471. Min Act: -0.0001

Data Index: 637113 (C4 (Web Text))

Max Activating Token Index: 565