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

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

Neuron 2899 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1313. Min Act: -0.0002

Data Index: 332700 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1065952 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1067477 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0931. Min Act: -0.0002

Data Index: 76388 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1278077 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1119644 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1045848 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0899. Min Act: -0.0002

Data Index: 3116 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0884. Min Act: -0.0002

Data Index: 310605 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1285548 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0881. Min Act: -0.0002

Data Index: 473335 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0850. Min Act: -0.0002

Data Index: 737182 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0841. Min Act: -0.0002

Data Index: 353238 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0843. Min Act: -0.0002

Data Index: 123504 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1339066 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0830. Min Act: -0.0002

Data Index: 571591 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0819. Min Act: -0.0002

Data Index: 853148 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0785. Min Act: -0.0002

Data Index: 454840 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1029047 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1352316 (C4 (Web Text))

Max Activating Token Index: 185