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

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

Neuron 1837 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: 0.7935. Min Range: -0.7935

Max Act: 0.7818. Min Act: -0.0001

Data Index: 197617 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7711. Min Act: -0.0001

Data Index: 372323 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1197990 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7777. Min Act: -0.0001

Data Index: 9328 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1196052 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7739. Min Act: -0.0001

Data Index: 379012 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7833. Min Act: -0.0001

Data Index: 542799 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7017. Min Act: -0.0001

Data Index: 514234 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7395. Min Act: -0.0001

Data Index: 630222 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6926. Min Act: -0.0001

Data Index: 530104 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6608. Min Act: -0.0001

Data Index: 1172660 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7447. Min Act: -0.0001

Data Index: 959860 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7130. Min Act: -0.0001

Data Index: 945020 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6794. Min Act: -0.0001

Data Index: 228371 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6502. Min Act: -0.0001

Data Index: 1094522 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6527. Min Act: -0.0001

Data Index: 296591 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7513. Min Act: -0.0001

Data Index: 964753 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1265233 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7005. Min Act: -0.0001

Data Index: 964221 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1278972 (C4 (Web Text))

Max Activating Token Index: 33