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

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

Neuron 2188 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3927. Min Act: -0.0003

Data Index: 786382 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3720. Min Act: -0.0003

Data Index: 944156 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3539. Min Act: -0.0003

Data Index: 1045992 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3499. Min Act: -0.0003

Data Index: 1008633 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3618. Min Act: -0.0003

Data Index: 16601 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3677. Min Act: -0.0003

Data Index: 1347223 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3428. Min Act: -0.0003

Data Index: 1277918 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3312. Min Act: -0.0003

Data Index: 242174 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3310. Min Act: -0.0003

Data Index: 134604 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3205. Min Act: -0.0003

Data Index: 362861 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3325. Min Act: -0.0003

Data Index: 271975 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3073. Min Act: -0.0003

Data Index: 818917 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3160. Min Act: -0.0003

Data Index: 854856 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3136. Min Act: -0.0003

Data Index: 896417 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3023. Min Act: -0.0003

Data Index: 476231 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3115. Min Act: -0.0003

Data Index: 384190 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3093. Min Act: -0.0003

Data Index: 869609 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3200. Min Act: -0.0003

Data Index: 1100771 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3094. Min Act: -0.0003

Data Index: 480272 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.3927. Min Range: -0.3927

Max Act: 0.3074. Min Act: -0.0003

Data Index: 374618 (C4 (Web Text))

Max Activating Token Index: 253