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

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

Neuron 1140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.3513. Min Act: -0.0000

Data Index: 282583 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1064578 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.3347. Min Act: -0.0000

Data Index: 603318 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2595. Min Act: -0.0000

Data Index: 544441 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1353. Min Act: -0.0000

Data Index: 717528 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2064. Min Act: -0.0000

Data Index: 550842 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0793. Min Act: -0.0000

Data Index: 919788 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1942. Min Act: -0.0000

Data Index: 430747 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0745. Min Act: 0.0000

Data Index: 1159817 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0179. Min Act: -0.0000

Data Index: 160810 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9430. Min Act: -0.0000

Data Index: 430252 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1355370 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9603. Min Act: -0.0000

Data Index: 824428 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1284490 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1043694 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9343. Min Act: 0.0000

Data Index: 236819 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1083234 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9206. Min Act: -0.0000

Data Index: 396666 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9221. Min Act: -0.0000

Data Index: 354701 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8996. Min Act: -0.0000

Data Index: 643598 (C4 (Web Text))

Max Activating Token Index: 584