Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1092081 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.1319. Min Act: -0.0000

Data Index: 75092 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0825. Min Act: -0.0000

Data Index: 643812 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0520. Min Act: -0.0000

Data Index: 549901 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.2332. Min Range: -1.2332

Max Act: 1.0107. Min Act: -0.0000

Data Index: 915877 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1188820 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9365. Min Act: -0.0000

Data Index: 475332 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9448. Min Act: -0.0001

Data Index: 728388 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8994. Min Act: -0.0000

Data Index: 39184 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8385. Min Act: -0.0000

Data Index: 302080 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1170191 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8515. Min Act: -0.0000

Data Index: 54287 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.9009. Min Act: -0.0000

Data Index: 759389 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8432. Min Act: -0.0000

Data Index: 965387 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8703. Min Act: -0.0000

Data Index: 619920 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8614. Min Act: -0.0000

Data Index: 483750 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1200535 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1084004 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8359. Min Act: -0.0000

Data Index: 152490 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.2332. Min Range: -1.2332

Max Act: 0.8284. Min Act: -0.0000

Data Index: 826954 (C4 (Web Text))

Max Activating Token Index: 740