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

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

Neuron 131 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.7199. Min Act: -0.0001

Data Index: 561869 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.6860. Min Act: -0.0001

Data Index: 43345 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.6825. Min Act: -0.0001

Data Index: 592464 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.5584. Min Act: -0.0001

Data Index: 195877 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.6451. Min Act: -0.0001

Data Index: 863032 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.6519. Min Act: -0.0001

Data Index: 615363 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.7150. Min Act: -0.0001

Data Index: 338643 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.5145. Min Act: -0.0001

Data Index: 226187 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.5360. Min Act: -0.0001

Data Index: 874851 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.5558. Min Act: -0.0001

Data Index: 833458 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.4579. Min Act: -0.0001

Data Index: 599299 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.4167. Min Act: -0.0001

Data Index: 1337500 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.4791. Min Act: -0.0001

Data Index: 213086 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.5314. Min Act: -0.0001

Data Index: 1204377 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.4045. Min Act: -0.0001

Data Index: 314109 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.2969. Min Act: -0.0001

Data Index: 184689 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.5045. Min Act: -0.0001

Data Index: 1338859 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.3737. Min Act: -0.0001

Data Index: 780027 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.3596. Min Act: -0.0001

Data Index: 731981 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.7199. Min Range: -1.7199

Max Act: 1.3693. Min Act: -0.0001

Data Index: 1235944 (C4 (Web Text))

Max Activating Token Index: 984