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

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

Neuron 4093 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.7859. Min Act: -0.0001

Data Index: 105297 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.1578. Min Act: -0.0001

Data Index: 208945 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.1904. Min Act: -0.0001

Data Index: 418536 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.3025. Min Act: -0.0001

Data Index: 162594 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.2284. Min Act: -0.0001

Data Index: 888999 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 3.7859. Min Range: -3.7859

Max Act: 3.1502. Min Act: -0.0001

Data Index: 1002037 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.8208. Min Act: -0.0001

Data Index: 1070721 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.9303. Min Act: -0.0001

Data Index: 818183 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.9416. Min Act: -0.0000

Data Index: 382286 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.8997. Min Act: -0.0001

Data Index: 535821 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.6897. Min Act: -0.0000

Data Index: 130767 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.8241. Min Act: -0.0001

Data Index: 420393 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.8268. Min Act: -0.0001

Data Index: 1283701 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.5450. Min Act: -0.0001

Data Index: 1048569 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.8138. Min Act: -0.0000

Data Index: 386902 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.7863. Min Act: -0.0001

Data Index: 1270685 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.7161. Min Act: -0.0001

Data Index: 1313764 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.8673. Min Act: -0.0001

Data Index: 314582 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.7247. Min Act: -0.0001

Data Index: 304021 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 3.7859. Min Range: -3.7859

Max Act: 2.5708. Min Act: -0.0001

Data Index: 608209 (C4 (Web Text))

Max Activating Token Index: 247