Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 886 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2947. Min Act: -0.0003

Data Index: 699317 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2792. Min Act: -0.0003

Data Index: 1085415 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2647. Min Act: -0.0003

Data Index: 20211 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2591. Min Act: -0.0003

Data Index: 511124 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2646. Min Act: -0.0003

Data Index: 359740 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2436. Min Act: -0.0004

Data Index: 1019885 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2517. Min Act: -0.0003

Data Index: 145465 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2475. Min Act: -0.0003

Data Index: 955003 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2365. Min Act: -0.0003

Data Index: 465191 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2423. Min Act: -0.0003

Data Index: 180686 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2281. Min Act: -0.0003

Data Index: 96909 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2265. Min Act: -0.0003

Data Index: 133540 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2379. Min Act: -0.0003

Data Index: 306009 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2278. Min Act: -0.0003

Data Index: 291717 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2212. Min Act: -0.0003

Data Index: 58787 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2207. Min Act: -0.0003

Data Index: 1011262 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2099. Min Act: -0.0003

Data Index: 892159 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2063. Min Act: -0.0003

Data Index: 945911 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2088. Min Act: -0.0003

Data Index: 339988 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1998. Min Act: -0.0003

Data Index: 367808 (C4 (Web Text))

Max Activating Token Index: 151