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

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

Neuron 2709 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.7125. Min Act: -0.0000

Data Index: 57580 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1307222 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.5125. Min Act: -0.0000

Data Index: 834930 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.5332. Min Act: -0.0000

Data Index: 62117 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1055163 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.3253. Min Act: -0.0000

Data Index: 61490 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1137127 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1227417 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1165315 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1342284 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.3482. Min Act: -0.0000

Data Index: 725782 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.2708. Min Act: -0.0000

Data Index: 227350 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.1891. Min Act: -0.0000

Data Index: 155069 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.2704. Min Act: -0.0000

Data Index: 51331 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.1631. Min Act: -0.0000

Data Index: 843659 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.4067. Min Act: -0.0000

Data Index: 994334 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1179678 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.0824. Min Act: -0.0000

Data Index: 188733 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1131651 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.7125. Min Range: -1.7125

Max Act: 1.2695. Min Act: -0.0000

Data Index: 982328 (C4 (Web Text))

Max Activating Token Index: 547