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

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

Neuron 1425 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.7187. Min Act: -0.0001

Data Index: 989951 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.6288. Min Act: -0.0001

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.6955. Min Act: -0.0001

Data Index: 969279 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.6175. Min Act: -0.0001

Data Index: 896549 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5303. Min Act: -0.0001

Data Index: 1220646 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5937. Min Act: -0.0001

Data Index: 893084 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5777. Min Act: -0.0001

Data Index: 160368 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4897. Min Act: -0.0001

Data Index: 806654 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4816. Min Act: -0.0001

Data Index: 746170 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5593. Min Act: -0.0001

Data Index: 197493 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4189. Min Act: -0.0001

Data Index: 342209 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3334. Min Act: -0.0001

Data Index: 674358 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3855. Min Act: -0.0001

Data Index: 260757 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4023. Min Act: -0.0001

Data Index: 1004081 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3668. Min Act: -0.0001

Data Index: 786832 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.2617. Min Act: -0.0001

Data Index: 689715 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3266. Min Act: -0.0001

Data Index: 855645 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4109. Min Act: -0.0001

Data Index: 258296 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4118. Min Act: -0.0001

Data Index: 954004 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3121. Min Act: -0.0001

Data Index: 340643 (C4 (Web Text))

Max Activating Token Index: 192