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

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

Neuron 5170 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.5200. Min Act: -0.0000

Data Index: 834560 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4623. Min Act: -0.0000

Data Index: 737399 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1165700 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.5090. Min Act: -0.0000

Data Index: 325944 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.5010. Min Act: -0.0000

Data Index: 565439 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4954. Min Act: -0.0000

Data Index: 631728 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4135. Min Act: -0.0000

Data Index: 351306 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1341256 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4813. Min Act: -0.0000

Data Index: 654472 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1209814 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4586. Min Act: -0.0000

Data Index: 636951 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1088973 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1204225 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1671 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.4382. Min Act: -0.0000

Data Index: 192444 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3955. Min Act: -0.0000

Data Index: 687051 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3934. Min Act: -0.0000

Data Index: 483043 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1102310 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3898. Min Act: -0.0000

Data Index: 311978 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.5200. Min Range: -0.5200

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1203183 (C4 (Web Text))

Max Activating Token Index: 283