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

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

Neuron 284 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: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1030465 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1159826 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0303. Min Act: -0.0004

Data Index: 1035111 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0003

Data Index: 959332 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0318. Min Act: -0.0003

Data Index: 270152 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0318. Min Act: -0.0003

Data Index: 279747 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0311. Min Act: -0.0003

Data Index: 161278 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0309. Min Act: -0.0002

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1169999 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1192132 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0293. Min Act: -0.0003

Data Index: 805620 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0282. Min Act: -0.0003

Data Index: 966830 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0285. Min Act: -0.0002

Data Index: 216294 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0295. Min Act: -0.0003

Data Index: 630310 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1065640 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0277. Min Act: -0.0003

Data Index: 921668 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0276. Min Act: -0.0004

Data Index: 625655 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1128103 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0281. Min Act: -0.0004

Data Index: 988020 (C4 (Web Text))

Max Activating Token Index: 100