Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5684. Min Act: -0.0001

Data Index: 544161 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5984. Min Act: -0.0001

Data Index: 853286 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.6852. Min Act: -0.0001

Data Index: 14459 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5319. Min Act: -0.0001

Data Index: 316332 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5685. Min Act: -0.0001

Data Index: 453146 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5631. Min Act: -0.0001

Data Index: 360486 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5230. Min Act: -0.0001

Data Index: 688803 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.4963. Min Act: -0.0001

Data Index: 106584 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.5129. Min Act: -0.0001

Data Index: 823017 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.4578. Min Act: -0.0001

Data Index: 1003431 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.4037. Min Act: -0.0001

Data Index: 581627 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.3028. Min Act: -0.0001

Data Index: 262644 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.3266. Min Act: -0.0001

Data Index: 983948 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.3515. Min Act: -0.0001

Data Index: 1071206 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.3476. Min Act: -0.0001

Data Index: 133962 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.2927. Min Act: -0.0001

Data Index: 1097637 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.2648. Min Act: -0.0001

Data Index: 1095938 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.2887. Min Act: -0.0001

Data Index: 288429 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.3568. Min Act: -0.0001

Data Index: 8937 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.6852. Min Range: -1.6852

Max Act: 1.1678. Min Act: -0.0001

Data Index: 799279 (C4 (Web Text))

Max Activating Token Index: 672