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

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

Neuron 3695 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1400880 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0499. Min Act: -0.0002

Data Index: 336546 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0400. Min Act: -0.0002

Data Index: 367927 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1275024 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1452775 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1208818 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0364. Min Act: -0.0002

Data Index: 785599 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1366947 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0352. Min Act: -0.0002

Data Index: 393764 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0349. Min Act: -0.0002

Data Index: 881688 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1414838 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1562156 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0322. Min Act: -0.0002

Data Index: 439514 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1424700 (Python Code)

Max Activating Token Index: 897

Text #14

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1505360 (Python Code)

Max Activating Token Index: 176

Text #15

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0318. Min Act: -0.0002

Data Index: 262197 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1481750 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1600162 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1475777 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.0576. Min Range: -0.0576

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1613374 (Python Code)

Max Activating Token Index: 677