Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1022892 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3791. Min Act: -0.0000

Data Index: 902866 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3578. Min Act: -0.0001

Data Index: 953719 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3413. Min Act: -0.0001

Data Index: 1185435 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3504. Min Act: -0.0001

Data Index: 82984 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3323. Min Act: -0.0001

Data Index: 588970 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3206. Min Act: -0.0000

Data Index: 477870 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2980. Min Act: -0.0000

Data Index: 50250 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2772. Min Act: -0.0001

Data Index: 939229 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2790. Min Act: -0.0001

Data Index: 894397 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2852. Min Act: -0.0001

Data Index: 1232509 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2657. Min Act: -0.0000

Data Index: 820843 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2731. Min Act: -0.0000

Data Index: 773735 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1212635 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2580. Min Act: -0.0000

Data Index: 710211 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1250114 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2643. Min Act: -0.0001

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2629. Min Act: -0.0000

Data Index: 558696 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2626. Min Act: -0.0001

Data Index: 45341 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1042474 (C4 (Web Text))

Max Activating Token Index: 709