Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3917 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4748. Min Act: -0.0001

Data Index: 599702 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.5138. Min Act: -0.0001

Data Index: 997542 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4039. Min Act: -0.0001

Data Index: 1357658 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.5230. Min Act: -0.0001

Data Index: 403073 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4572. Min Act: -0.0001

Data Index: 62075 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.5328. Min Act: -0.0001

Data Index: 814723 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4048. Min Act: -0.0001

Data Index: 166796 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4723. Min Act: -0.0001

Data Index: 221052 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4213. Min Act: -0.0001

Data Index: 292757 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4596. Min Act: -0.0001

Data Index: 180744 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3389. Min Act: -0.0001

Data Index: 964324 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3168. Min Act: -0.0001

Data Index: 179808 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3798. Min Act: -0.0001

Data Index: 1299422 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4231. Min Act: -0.0001

Data Index: 102127 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4980. Min Act: -0.0001

Data Index: 1275882 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.4087. Min Act: -0.0001

Data Index: 345765 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3209. Min Act: -0.0001

Data Index: 561266 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3591. Min Act: -0.0001

Data Index: 1089828 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3937. Min Act: -0.0001

Data Index: 50702 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 1.5328. Min Range: -1.5328

Max Act: 1.3568. Min Act: -0.0001

Data Index: 404987 (C4 (Web Text))

Max Activating Token Index: 350