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

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

Neuron 4408 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: 1.6137. Min Range: -1.6137

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1135848 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3736. Min Act: -0.0000

Data Index: 220847 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.4456. Min Act: -0.0000

Data Index: 484827 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2989. Min Act: -0.0000

Data Index: 1150107 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1240146 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3159. Min Act: -0.0000

Data Index: 979647 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3222. Min Act: 0.0000

Data Index: 1066178 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2280. Min Act: -0.0000

Data Index: 128163 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2089. Min Act: -0.0000

Data Index: 362071 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1841. Min Act: -0.0000

Data Index: 707268 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2534. Min Act: -0.0000

Data Index: 439659 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1015. Min Act: -0.0000

Data Index: 819555 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2351. Min Act: -0.0000

Data Index: 823049 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1594. Min Act: -0.0000

Data Index: 470137 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2046. Min Act: -0.0000

Data Index: 203062 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1084115 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1697. Min Act: -0.0000

Data Index: 204620 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1986. Min Act: -0.0000

Data Index: 722364 (C4 (Web Text))

Max Activating Token Index: 970