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

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

Neuron 1764 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: 0.7240. Min Range: -0.7240

Max Act: 0.5912. Min Act: -0.0001

Data Index: 754772 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.6675. Min Act: -0.0001

Data Index: 1079948 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5989. Min Act: -0.0001

Data Index: 75828 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.6054. Min Act: -0.0001

Data Index: 1181874 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1337072 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.6275. Min Act: -0.0001

Data Index: 768561 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5597. Min Act: -0.0001

Data Index: 994376 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5528. Min Act: -0.0001

Data Index: 408702 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.7240. Min Act: -0.0001

Data Index: 162291 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5721. Min Act: -0.0001

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5420. Min Act: -0.0001

Data Index: 244102 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5704. Min Act: -0.0001

Data Index: 411237 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5500. Min Act: -0.0001

Data Index: 212929 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5458. Min Act: -0.0001

Data Index: 1093972 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5313. Min Act: -0.0001

Data Index: 691423 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5425. Min Act: -0.0001

Data Index: 328786 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.4920. Min Act: -0.0001

Data Index: 115014 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5709. Min Act: -0.0001

Data Index: 807553 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5141. Min Act: -0.0001

Data Index: 113486 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.7240. Min Range: -0.7240

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1001215 (C4 (Web Text))

Max Activating Token Index: 284