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

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

Neuron 1041 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.4281. Min Act: -0.0001

Data Index: 154721 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3748. Min Act: -0.0001

Data Index: 1347547 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3442. Min Act: -0.0001

Data Index: 576193 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3703. Min Act: -0.0001

Data Index: 519346 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3470. Min Act: -0.0001

Data Index: 731145 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3639. Min Act: -0.0001

Data Index: 287264 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3087. Min Act: -0.0001

Data Index: 596640 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1354584 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3259. Min Act: -0.0001

Data Index: 282567 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3022. Min Act: -0.0001

Data Index: 383363 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3394. Min Act: -0.0001

Data Index: 1288314 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3334. Min Act: -0.0001

Data Index: 565686 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3699. Min Act: -0.0001

Data Index: 139710 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.2844. Min Act: -0.0001

Data Index: 368092 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3125. Min Act: -0.0001

Data Index: 154017 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3206. Min Act: -0.0001

Data Index: 943390 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3210. Min Act: -0.0001

Data Index: 731773 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.3254. Min Act: -0.0001

Data Index: 726055 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.2845. Min Act: -0.0001

Data Index: 389217 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.4281. Min Range: -0.4281

Max Act: 0.2976. Min Act: -0.0001

Data Index: 1041934 (C4 (Web Text))

Max Activating Token Index: 658