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

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

Neuron 1627 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: 0.4430. Min Range: -0.4430

Max Act: 0.4430. Min Act: -0.0001

Data Index: 814395 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4284. Min Act: -0.0001

Data Index: 1033722 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1321149 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4207. Min Act: -0.0001

Data Index: 640028 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4218. Min Act: -0.0001

Data Index: 778646 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4171. Min Act: -0.0001

Data Index: 512446 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3832. Min Act: -0.0001

Data Index: 540649 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3903. Min Act: -0.0001

Data Index: 154413 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3791. Min Act: -0.0001

Data Index: 575988 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.4369. Min Act: -0.0001

Data Index: 814437 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1160211 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3500. Min Act: -0.0001

Data Index: 1285 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3930. Min Act: -0.0001

Data Index: 185069 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3621. Min Act: -0.0001

Data Index: 836284 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3952. Min Act: -0.0001

Data Index: 994268 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3925. Min Act: -0.0001

Data Index: 431098 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3804. Min Act: -0.0001

Data Index: 505913 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1045181 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3530. Min Act: -0.0001

Data Index: 392706 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.4430. Min Range: -0.4430

Max Act: 0.3843. Min Act: -0.0001

Data Index: 1345049 (C4 (Web Text))

Max Activating Token Index: 349