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

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

Neuron 3996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1065998 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1141136 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1325031 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4567. Min Act: -0.0000

Data Index: 145718 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4809. Min Act: -0.0000

Data Index: 775975 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4630. Min Act: -0.0000

Data Index: 282367 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4617. Min Act: -0.0000

Data Index: 583732 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4105. Min Act: -0.0000

Data Index: 129568 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4206. Min Act: -0.0000

Data Index: 298231 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4252. Min Act: -0.0000

Data Index: 806188 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4156. Min Act: -0.0000

Data Index: 888948 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4013. Min Act: -0.0000

Data Index: 921949 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1169078 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1320283 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4304. Min Act: -0.0000

Data Index: 561962 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4105. Min Act: -0.0000

Data Index: 261229 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4257. Min Act: -0.0000

Data Index: 714447 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1105628 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.4029. Min Act: -0.0000

Data Index: 543710 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.6147. Min Range: -0.6147

Max Act: 0.3938. Min Act: -0.0000

Data Index: 748707 (C4 (Web Text))

Max Activating Token Index: 721