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

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

Neuron 5246 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: 0.0438. Min Range: -0.0438

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1224054 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0437. Min Act: -0.0001

Data Index: 845104 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1376203 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0378. Min Act: -0.0001

Data Index: 273198 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0421. Min Act: -0.0001

Data Index: 367857 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0373. Min Act: -0.0001

Data Index: 100744 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0397. Min Act: -0.0001

Data Index: 245654 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0001

Data Index: 877068 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0414. Min Act: -0.0001

Data Index: 204757 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1306675 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1519326 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1408942 (Python Code)

Max Activating Token Index: 48

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1135968 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0308. Min Act: -0.0001

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0321. Min Act: -0.0001

Data Index: 861866 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0301. Min Act: -0.0001

Data Index: 583462 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0313. Min Act: -0.0001

Data Index: 97792 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1451915 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0333. Min Act: -0.0001

Data Index: 273337 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1638786 (Python Code)

Max Activating Token Index: 148