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

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

Neuron 4954 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.9386. Min Act: -0.0000

Data Index: 305657 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.3816. Min Act: -0.0000

Data Index: 17832 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.3079. Min Act: -0.0000

Data Index: 55458 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.4184. Min Act: -0.0000

Data Index: 35934 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.3031. Min Act: -0.0001

Data Index: 695462 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.3870. Min Act: -0.0001

Data Index: 196542 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.2755. Min Act: -0.0001

Data Index: 606916 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.2511. Min Act: -0.0001

Data Index: 217588 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.0704. Min Act: -0.0001

Data Index: 334346 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.1809. Min Act: -0.0001

Data Index: 225579 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.1645. Min Act: -0.0001

Data Index: 258250 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.2846. Min Act: -0.0001

Data Index: 1159984 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.2711. Min Act: -0.0000

Data Index: 492639 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.0486. Min Act: -0.0000

Data Index: 485740 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.1475. Min Act: -0.0000

Data Index: 906334 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.1171. Min Act: -0.0000

Data Index: 250243 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1175018 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.1152. Min Act: -0.0000

Data Index: 779647 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.9386. Min Range: -2.9386

Max Act: 2.0919. Min Act: -0.0000

Data Index: 79594 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 2.9386. Min Range: -2.9386

Max Act: 1.9400. Min Act: -0.0000

Data Index: 406806 (C4 (Web Text))

Max Activating Token Index: 728