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

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

Neuron 50 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1287196 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0432. Min Act: -0.0003

Data Index: 987875 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0432. Min Act: -0.0003

Data Index: 59575 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1197895 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0405. Min Act: -0.0002

Data Index: 442874 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1020573 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0410. Min Act: -0.0003

Data Index: 669086 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0398. Min Act: -0.0002

Data Index: 565238 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0397. Min Act: -0.0003

Data Index: 638819 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1062137 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0399. Min Act: -0.0002

Data Index: 610140 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1231218 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0396. Min Act: -0.0003

Data Index: 473870 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0391. Min Act: -0.0002

Data Index: 50180 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1279880 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1173453 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0392. Min Act: -0.0002

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1157127 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0388. Min Act: -0.0003

Data Index: 456368 (C4 (Web Text))

Max Activating Token Index: 265