Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1554 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1081161 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3665. Min Act: -0.0000

Data Index: 8020 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1615586 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1080815 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3411. Min Act: -0.0000

Data Index: 613014 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3186. Min Act: -0.0000

Data Index: 612315 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3118. Min Act: -0.0000

Data Index: 40640 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3349. Min Act: 0.0003

Data Index: 618971 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3554. Min Act: -0.0000

Data Index: 825793 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3284. Min Act: -0.0000

Data Index: 290643 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3404. Min Act: -0.0000

Data Index: 509317 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1378855 (Python Code)

Max Activating Token Index: 90

Text #12

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1121173 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3090. Min Act: 0.0004

Data Index: 287435 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3067. Min Act: 0.0005

Data Index: 1414603 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3258. Min Act: -0.0000

Data Index: 657801 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3213. Min Act: 0.0000

Data Index: 1403007 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3115. Min Act: 0.0002

Data Index: 815790 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3045. Min Act: -0.0000

Data Index: 861641 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.2978. Min Act: 0.0009

Data Index: 1050749 (C4 (Web Text))

Max Activating Token Index: 364