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

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

Neuron 1603 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: 1.9054. Min Range: -1.9054

Max Act: 1.8840. Min Act: -0.0001

Data Index: 903778 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.8833. Min Act: -0.0001

Data Index: 1079117 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.9054. Min Act: -0.0001

Data Index: 719500 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.7704. Min Act: -0.0001

Data Index: 521778 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6506. Min Act: -0.0001

Data Index: 10816 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.7564. Min Act: -0.0001

Data Index: 538402 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.8181. Min Act: -0.0001

Data Index: 137070 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6864. Min Act: -0.0001

Data Index: 1103985 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6023. Min Act: -0.0001

Data Index: 402458 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.7469. Min Act: -0.0001

Data Index: 979035 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6383. Min Act: -0.0001

Data Index: 418180 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6535. Min Act: -0.0001

Data Index: 996310 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6249. Min Act: -0.0001

Data Index: 535657 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6871. Min Act: -0.0001

Data Index: 474398 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.5739. Min Act: -0.0001

Data Index: 314860 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.4514. Min Act: -0.0001

Data Index: 1264614 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.6111. Min Act: -0.0001

Data Index: 305482 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.5218. Min Act: -0.0001

Data Index: 917674 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.5102. Min Act: -0.0001

Data Index: 1045207 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.9054. Min Range: -1.9054

Max Act: 1.4192. Min Act: -0.0001

Data Index: 1208870 (C4 (Web Text))

Max Activating Token Index: 505