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

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

Neuron 135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.3761. Min Act: -0.0000

Data Index: 219815 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.2453. Min Act: -0.0000

Data Index: 973310 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1343410 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.3288. Min Act: -0.0000

Data Index: 219044 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.4231. Min Act: -0.0000

Data Index: 930815 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.1797. Min Act: -0.0000

Data Index: 732518 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.3010. Min Act: -0.0000

Data Index: 658682 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.2579. Min Act: -0.0000

Data Index: 595622 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.2312. Min Act: -0.0000

Data Index: 678506 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.2147. Min Act: -0.0000

Data Index: 303805 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.2096. Min Act: -0.0000

Data Index: 126405 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.1973. Min Act: -0.0000

Data Index: 1221061 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.1137. Min Act: -0.0000

Data Index: 173019 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.1027. Min Act: -0.0000

Data Index: 341643 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.1044. Min Act: -0.0000

Data Index: 1200813 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.0871. Min Act: -0.0000

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.0787. Min Act: -0.0000

Data Index: 1049957 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 2.4231. Min Range: -2.4231

Max Act: 2.0822. Min Act: -0.0000

Data Index: 1327017 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.4231. Min Range: -2.4231

Max Act: 1.9542. Min Act: -0.0000

Data Index: 101142 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 2.4231. Min Range: -2.4231

Max Act: 1.9617. Min Act: -0.0000

Data Index: 40178 (C4 (Web Text))

Max Activating Token Index: 137