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

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

Neuron 5745 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.7459. Min Act: -0.0002

Data Index: 1047033 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.7451. Min Act: -0.0002

Data Index: 664296 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6411. Min Act: -0.0002

Data Index: 316049 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6022. Min Act: -0.0002

Data Index: 902872 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6561. Min Act: -0.0002

Data Index: 729962 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6199. Min Act: -0.0002

Data Index: 66058 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6116. Min Act: -0.0002

Data Index: 1013779 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5937. Min Act: -0.0002

Data Index: 893862 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5487. Min Act: -0.0002

Data Index: 1350326 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5649. Min Act: -0.0002

Data Index: 538092 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5787. Min Act: -0.0002

Data Index: 1242675 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5566. Min Act: -0.0002

Data Index: 957591 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5189. Min Act: -0.0002

Data Index: 1303040 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5716. Min Act: -0.0002

Data Index: 700382 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5482. Min Act: -0.0002

Data Index: 1114141 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5115. Min Act: -0.0002

Data Index: 863573 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5171. Min Act: -0.0002

Data Index: 980452 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5362. Min Act: -0.0002

Data Index: 156129 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5302. Min Act: -0.0002

Data Index: 207174 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5243. Min Act: -0.0002

Data Index: 356219 (C4 (Web Text))

Max Activating Token Index: 257