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

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

Neuron 2900 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.4250. Min Act: -0.0001

Data Index: 284070 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.4090. Min Act: -0.0001

Data Index: 907160 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.4005. Min Act: -0.0001

Data Index: 918413 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.3368. Min Act: -0.0001

Data Index: 1222990 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.3515. Min Act: -0.0001

Data Index: 614714 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.3903. Min Act: -0.0001

Data Index: 384306 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.3720. Min Act: -0.0001

Data Index: 718558 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.2264. Min Act: -0.0001

Data Index: 1211672 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.2560. Min Act: -0.0001

Data Index: 289398 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1903. Min Act: -0.0001

Data Index: 561742 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1116205 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1647. Min Act: -0.0001

Data Index: 976595 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1385. Min Act: -0.0001

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.0528. Min Act: -0.0001

Data Index: 832281 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1264. Min Act: -0.0001

Data Index: 545262 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1466. Min Act: -0.0001

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.0978. Min Act: -0.0001

Data Index: 1182432 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.1130. Min Act: -0.0001

Data Index: 282428 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.0875. Min Act: -0.0001

Data Index: 988883 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 1.4250. Min Range: -1.4250

Max Act: 1.0692. Min Act: -0.0001

Data Index: 919550 (C4 (Web Text))

Max Activating Token Index: 217