Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0002

Data Index: 824073 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0294. Min Act: -0.0003

Data Index: 893248 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0291. Min Act: -0.0002

Data Index: 884567 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0277. Min Act: -0.0002

Data Index: 899610 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1063988 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0264. Min Act: -0.0002

Data Index: 792853 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0274. Min Act: -0.0002

Data Index: 963765 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1083338 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0261. Min Act: -0.0002

Data Index: 568192 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0264. Min Act: -0.0002

Data Index: 520973 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0260. Min Act: -0.0002

Data Index: 772665 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0263. Min Act: -0.0002

Data Index: 195197 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0255. Min Act: -0.0002

Data Index: 803224 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0256. Min Act: -0.0002

Data Index: 792504 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0267. Min Act: -0.0002

Data Index: 482424 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0259. Min Act: -0.0002

Data Index: 270338 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0262. Min Act: -0.0002

Data Index: 552364 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0253. Min Act: -0.0002

Data Index: 288998 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0259. Min Act: -0.0002

Data Index: 802036 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1328479 (C4 (Web Text))

Max Activating Token Index: 120