Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 445 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0006

Data Index: 479056 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0292. Min Act: -0.0006

Data Index: 633818 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0280. Min Act: -0.0006

Data Index: 913498 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0285. Min Act: -0.0006

Data Index: 970321 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1282182 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0275. Min Act: -0.0006

Data Index: 371482 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0284. Min Act: -0.0006

Data Index: 784503 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0276. Min Act: -0.0006

Data Index: 866316 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0266. Min Act: -0.0006

Data Index: 282978 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0257. Min Act: -0.0006

Data Index: 428115 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0277. Min Act: -0.0006

Data Index: 726502 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0277. Min Act: -0.0006

Data Index: 297668 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0263. Min Act: -0.0006

Data Index: 647427 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0255. Min Act: -0.0006

Data Index: 976131 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0261. Min Act: -0.0006

Data Index: 777648 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0244. Min Act: -0.0006

Data Index: 294078 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1305238 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0253. Min Act: -0.0006

Data Index: 697519 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0258. Min Act: -0.0006

Data Index: 896446 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1329273 (C4 (Web Text))

Max Activating Token Index: 173