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

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

Neuron 1947 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: 0.6498. Min Range: -0.6498

Max Act: 0.6498. Min Act: -0.0000

Data Index: 515656 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1090478 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4184. Min Act: -0.0000

Data Index: 881937 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4108. Min Act: -0.0000

Data Index: 280010 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.3896. Min Act: -0.0000

Data Index: 167594 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4712. Min Act: -0.0000

Data Index: 455844 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4254. Min Act: -0.0000

Data Index: 930874 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4228. Min Act: -0.0000

Data Index: 270230 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4210. Min Act: -0.0000

Data Index: 210445 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4078. Min Act: -0.0000

Data Index: 438082 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4481. Min Act: -0.0000

Data Index: 142775 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4179. Min Act: -0.0000

Data Index: 220552 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4260. Min Act: -0.0000

Data Index: 816305 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1173922 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.3941. Min Act: -0.0000

Data Index: 646592 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4299. Min Act: -0.0000

Data Index: 78548 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1242016 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1045153 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.3765. Min Act: -0.0000

Data Index: 802250 (C4 (Web Text))

Max Activating Token Index: 951