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

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

Neuron 3864 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.7407. Min Act: -0.0000

Data Index: 1172798 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.7297. Min Act: -0.0000

Data Index: 11558 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.6046. Min Act: -0.0000

Data Index: 388178 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.2407. Min Act: -0.0000

Data Index: 416063 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.4030. Min Act: -0.0000

Data Index: 516627 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.9982. Min Act: -0.0000

Data Index: 11190 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.1659. Min Act: -0.0000

Data Index: 1023472 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 4.7407. Min Range: -4.7407

Max Act: 4.0760. Min Act: -0.0000

Data Index: 315410 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8374. Min Act: -0.0000

Data Index: 1266785 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.9071. Min Act: -0.0000

Data Index: 74039 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8805. Min Act: -0.0000

Data Index: 980846 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8856. Min Act: -0.0000

Data Index: 863302 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8523. Min Act: -0.0000

Data Index: 972036 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.4802. Min Act: -0.0000

Data Index: 132518 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.8144. Min Act: -0.0000

Data Index: 613836 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.9751. Min Act: -0.0000

Data Index: 506743 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.9399. Min Act: -0.0000

Data Index: 517782 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.7626. Min Act: -0.0000

Data Index: 684330 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.7628. Min Act: -0.0000

Data Index: 4253 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 4.7407. Min Range: -4.7407

Max Act: 3.6225. Min Act: -0.0000

Data Index: 280055 (C4 (Web Text))

Max Activating Token Index: 375