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

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

Neuron 161 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5699. Min Range: -2.5699

Max Act: 2.3513. Min Act: -0.0000

Data Index: 947964 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.5699. Min Range: -2.5699

Max Act: 2.5699. Min Act: 0.0001

Data Index: 78776 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.5699. Min Range: -2.5699

Max Act: 2.1805. Min Act: -0.0000

Data Index: 376814 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.8326. Min Act: -0.0000

Data Index: 12422 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.7666. Min Act: -0.0000

Data Index: 1322261 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.7518. Min Act: -0.0000

Data Index: 791577 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.7301. Min Act: -0.0000

Data Index: 768115 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.6943. Min Act: -0.0000

Data Index: 385467 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1205758 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.5960. Min Act: -0.0000

Data Index: 742132 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1117510 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.6904. Min Act: -0.0000

Data Index: 781136 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.5723. Min Act: -0.0000

Data Index: 587698 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.6621. Min Act: -0.0000

Data Index: 1279166 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.5737. Min Act: 0.0000

Data Index: 872827 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1293854 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.5409. Min Act: -0.0000

Data Index: 1017560 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.5004. Min Act: 0.0000

Data Index: 1590221 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.3959. Min Act: 0.0001

Data Index: 160705 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 2.5699. Min Range: -2.5699

Max Act: 1.4840. Min Act: 0.0001

Data Index: 1307094 (C4 (Web Text))

Max Activating Token Index: 999