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

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

Neuron 1670 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8722. Min Act: -0.0001

Data Index: 792510 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7485. Min Act: -0.0001

Data Index: 924894 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7111. Min Act: -0.0001

Data Index: 493488 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1249448 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.5118. Min Act: -0.0001

Data Index: 730587 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.5419. Min Act: -0.0001

Data Index: 1085891 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.5557. Min Act: -0.0001

Data Index: 526662 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.5510. Min Act: -0.0001

Data Index: 361273 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.4193. Min Act: -0.0001

Data Index: 834466 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.5409. Min Act: -0.0001

Data Index: 1067986 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1274270 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.4874. Min Act: -0.0001

Data Index: 251197 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.4549. Min Act: -0.0001

Data Index: 488322 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.3848. Min Act: -0.0001

Data Index: 615929 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.4091. Min Act: -0.0001

Data Index: 905917 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.3906. Min Act: -0.0001

Data Index: 60234 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.3670. Min Act: -0.0001

Data Index: 6802 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.3793. Min Act: -0.0001

Data Index: 977176 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.3661. Min Act: -0.0001

Data Index: 898876 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1198849 (C4 (Web Text))

Max Activating Token Index: 218