Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1323983 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1333127 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1018799 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.3017. Min Act: -0.0000

Data Index: 275149 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2846. Min Act: -0.0000

Data Index: 241104 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2622. Min Act: -0.0000

Data Index: 586689 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2749. Min Act: -0.0000

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2653. Min Act: -0.0000

Data Index: 424471 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1167445 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2425. Min Act: -0.0000

Data Index: 893629 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1161345 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1215608 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2199. Min Act: -0.0000

Data Index: 464056 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2444. Min Act: -0.0000

Data Index: 8701 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2521. Min Act: -0.0000

Data Index: 420729 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2338. Min Act: -0.0000

Data Index: 867775 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1120098 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2472. Min Act: -0.0000

Data Index: 713833 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2342. Min Act: -0.0000

Data Index: 774319 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1189501 (C4 (Web Text))

Max Activating Token Index: 895