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

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

Neuron 3999 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.8049. Min Act: -0.0001

Data Index: 131248 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6894. Min Act: -0.0001

Data Index: 135902 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6890. Min Act: -0.0001

Data Index: 677546 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6740. Min Act: -0.0001

Data Index: 1338912 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6660. Min Act: -0.0001

Data Index: 105340 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6471. Min Act: -0.0001

Data Index: 510113 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6305. Min Act: -0.0001

Data Index: 86794 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6685. Min Act: -0.0001

Data Index: 40530 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1330805 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6395. Min Act: -0.0001

Data Index: 95062 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5773. Min Act: -0.0001

Data Index: 1114039 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6211. Min Act: -0.0001

Data Index: 943132 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6295. Min Act: -0.0001

Data Index: 902233 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5420. Min Act: -0.0001

Data Index: 1274596 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5200. Min Act: -0.0001

Data Index: 333712 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6475. Min Act: -0.0001

Data Index: 32432 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5907. Min Act: -0.0001

Data Index: 136105 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5146. Min Act: -0.0001

Data Index: 113069 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6295. Min Act: -0.0001

Data Index: 960844 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7186. Min Act: -0.0001

Data Index: 845939 (C4 (Web Text))

Max Activating Token Index: 200