Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1123 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0002

Data Index: 875881 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1477. Min Act: -0.0002

Data Index: 472968 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1588. Min Act: -0.0002

Data Index: 1080308 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1526. Min Act: -0.0002

Data Index: 399615 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1306161 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1387. Min Act: -0.0001

Data Index: 785811 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1359. Min Act: -0.0001

Data Index: 518723 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1411. Min Act: -0.0002

Data Index: 988042 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1400. Min Act: -0.0002

Data Index: 657710 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1393. Min Act: -0.0002

Data Index: 912028 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1388. Min Act: -0.0002

Data Index: 380977 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1381. Min Act: -0.0002

Data Index: 637181 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1314. Min Act: -0.0002

Data Index: 973802 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1354. Min Act: -0.0002

Data Index: 905167 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1339. Min Act: -0.0001

Data Index: 908274 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1326. Min Act: -0.0001

Data Index: 941157 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1362. Min Act: -0.0002

Data Index: 343458 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1271. Min Act: -0.0002

Data Index: 584370 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1303. Min Act: -0.0002

Data Index: 146696 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1336. Min Act: -0.0002

Data Index: 2642 (C4 (Web Text))

Max Activating Token Index: 411