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

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

Neuron 134 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.4396. Min Act: -0.0000

Data Index: 469092 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2720. Min Act: -0.0000

Data Index: 525662 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2763. Min Act: -0.0000

Data Index: 998485 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2062. Min Act: -0.0000

Data Index: 804250 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2764. Min Act: -0.0000

Data Index: 501994 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1308076 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2379. Min Act: -0.0000

Data Index: 162506 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1180676 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1575. Min Act: -0.0000

Data Index: 827904 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1182. Min Act: -0.0000

Data Index: 788816 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9821. Min Act: -0.0000

Data Index: 686465 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1149295 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9742. Min Act: -0.0000

Data Index: 819286 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0377. Min Act: -0.0000

Data Index: 378434 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9399. Min Act: -0.0000

Data Index: 575683 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9965. Min Act: -0.0000

Data Index: 848264 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9192. Min Act: -0.0000

Data Index: 716816 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.8882. Min Act: -0.0000

Data Index: 170 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.8713. Min Act: -0.0000

Data Index: 849445 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.8479. Min Act: -0.0000

Data Index: 714276 (C4 (Web Text))

Max Activating Token Index: 892