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

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

Neuron 2105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1225885 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7943. Min Act: -0.0000

Data Index: 909781 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1330348 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7948. Min Act: -0.0000

Data Index: 616022 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7715. Min Act: -0.0000

Data Index: 163103 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8128. Min Act: -0.0000

Data Index: 921172 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7908. Min Act: -0.0000

Data Index: 668494 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7336. Min Act: -0.0000

Data Index: 579936 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7383. Min Act: -0.0000

Data Index: 90241 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7349. Min Act: -0.0000

Data Index: 816612 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7311. Min Act: -0.0000

Data Index: 274616 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6619. Min Act: -0.0000

Data Index: 774712 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7509. Min Act: -0.0000

Data Index: 744966 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1148191 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7055. Min Act: -0.0000

Data Index: 427127 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6880. Min Act: -0.0000

Data Index: 716421 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7683. Min Act: -0.0000

Data Index: 810669 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7959. Min Act: -0.0000

Data Index: 313246 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7916. Min Act: -0.0000

Data Index: 686239 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7596. Min Act: -0.0000

Data Index: 816462 (C4 (Web Text))

Max Activating Token Index: 716