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

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

Neuron 3174 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.2058. Min Act: -0.0001

Data Index: 248074 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1619. Min Act: -0.0001

Data Index: 490649 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.2226. Min Act: -0.0001

Data Index: 37098 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.2006. Min Act: -0.0001

Data Index: 1274875 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1965. Min Act: -0.0001

Data Index: 536009 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0909. Min Act: -0.0001

Data Index: 879337 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1575. Min Act: -0.0001

Data Index: 397045 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1557. Min Act: -0.0001

Data Index: 726968 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1156. Min Act: -0.0001

Data Index: 461029 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1055. Min Act: -0.0001

Data Index: 457272 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0752. Min Act: -0.0001

Data Index: 1069738 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0717. Min Act: -0.0001

Data Index: 109389 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1332. Min Act: -0.0001

Data Index: 397656 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.2226. Min Range: -1.2226

Max Act: 0.9779. Min Act: -0.0001

Data Index: 1613941 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1544. Min Act: -0.0001

Data Index: 1073076 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1296. Min Act: -0.0001

Data Index: 1168827 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0877. Min Act: -0.0001

Data Index: 429362 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.1164. Min Act: -0.0001

Data Index: 749921 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0992. Min Act: -0.0001

Data Index: 103082 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.2226. Min Range: -1.2226

Max Act: 1.0751. Min Act: -0.0001

Data Index: 260460 (C4 (Web Text))

Max Activating Token Index: 222