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

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

Neuron 202 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.8046. Min Act: -0.0000

Data Index: 1022806 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.6728. Min Act: -0.0000

Data Index: 865703 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.8123. Min Act: -0.0000

Data Index: 1158802 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.7188. Min Act: -0.0000

Data Index: 364477 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.6205. Min Act: -0.0000

Data Index: 307928 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1283624 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.4091. Min Act: -0.0000

Data Index: 789588 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.4100. Min Act: -0.0000

Data Index: 235505 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.4956. Min Act: -0.0000

Data Index: 229755 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.5479. Min Act: -0.0000

Data Index: 734705 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1221842 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.5292. Min Act: -0.0000

Data Index: 206399 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1146010 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.3629. Min Act: -0.0000

Data Index: 1272358 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.2279. Min Act: -0.0000

Data Index: 581483 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.2133. Min Act: -0.0000

Data Index: 972174 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.4071. Min Act: -0.0000

Data Index: 839342 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.1585. Min Act: -0.0000

Data Index: 257524 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.2301. Min Act: -0.0000

Data Index: 253817 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 1.8123. Min Range: -1.8123

Max Act: 1.1960. Min Act: -0.0000

Data Index: 1096125 (C4 (Web Text))

Max Activating Token Index: 516