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

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

Neuron 62 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0004

Data Index: 148149 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1022738 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0418. Min Act: -0.0002

Data Index: 329284 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0410. Min Act: -0.0002

Data Index: 535659 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0401. Min Act: -0.0003

Data Index: 854181 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0379. Min Act: -0.0003

Data Index: 383439 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0379. Min Act: -0.0003

Data Index: 393799 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1001498 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0354. Min Act: -0.0003

Data Index: 105921 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0368. Min Act: -0.0003

Data Index: 668270 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1101284 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0367. Min Act: -0.0003

Data Index: 683272 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0359. Min Act: -0.0004

Data Index: 404985 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0372. Min Act: -0.0003

Data Index: 880672 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0360. Min Act: -0.0003

Data Index: 821950 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0346. Min Act: -0.0003

Data Index: 321697 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0344. Min Act: -0.0003

Data Index: 70310 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0343. Min Act: -0.0003

Data Index: 538640 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0355. Min Act: -0.0003

Data Index: 517012 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0348. Min Act: -0.0003

Data Index: 445993 (C4 (Web Text))

Max Activating Token Index: 453