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

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

Neuron 232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2237. Min Act: -0.0001

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0609. Min Act: -0.0001

Data Index: 779951 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0927. Min Act: -0.0001

Data Index: 463080 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1290. Min Act: -0.0001

Data Index: 764031 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0478. Min Act: -0.0001

Data Index: 870403 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1401. Min Act: -0.0001

Data Index: 903431 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1293. Min Act: -0.0001

Data Index: 1333247 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1458. Min Act: -0.0001

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0143. Min Act: -0.0001

Data Index: 250718 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9506. Min Act: -0.0001

Data Index: 1220284 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9035. Min Act: -0.0001

Data Index: 1269570 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9081. Min Act: -0.0001

Data Index: 758578 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9628. Min Act: -0.0001

Data Index: 1199534 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9293. Min Act: -0.0001

Data Index: 453363 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9132. Min Act: -0.0001

Data Index: 1115380 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.9268. Min Act: -0.0001

Data Index: 1210059 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7390. Min Act: -0.0001

Data Index: 182337 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1250174 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8990. Min Act: -0.0001

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8959. Min Act: -0.0001

Data Index: 867283 (C4 (Web Text))

Max Activating Token Index: 470