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

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

Neuron 1571 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5723. Min Act: -0.0000

Data Index: 145916 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1231722 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3586. Min Act: -0.0000

Data Index: 84042 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3382. Min Act: -0.0000

Data Index: 563943 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.2497. Min Act: -0.0000

Data Index: 985110 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.2077. Min Act: -0.0000

Data Index: 46083 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.3019. Min Act: -0.0000

Data Index: 79870 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1305986 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0754. Min Act: -0.0000

Data Index: 317613 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0797. Min Act: -0.0000

Data Index: 92301 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.1397. Min Act: -0.0000

Data Index: 313428 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9731. Min Act: -0.0000

Data Index: 93601 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0238. Min Act: -0.0000

Data Index: 976915 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0143. Min Act: -0.0000

Data Index: 58602 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8940. Min Act: -0.0000

Data Index: 390366 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0009. Min Act: -0.0000

Data Index: 153713 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1002661 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0938. Min Act: -0.0000

Data Index: 310532 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.7823. Min Act: -0.0000

Data Index: 606360 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1278222 (C4 (Web Text))

Max Activating Token Index: 237