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

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

Neuron 267 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.7484. Min Act: -0.0000

Data Index: 318754 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.6198. Min Act: -0.0000

Data Index: 1039450 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.6796. Min Act: -0.0000

Data Index: 324349 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1213239 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.8303. Min Act: -0.0000

Data Index: 38341 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.9094. Min Act: -0.0000

Data Index: 1199276 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.6116. Min Act: -0.0000

Data Index: 448966 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.8043. Min Act: -0.0000

Data Index: 250881 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.4861. Min Act: -0.0000

Data Index: 1202296 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2202. Min Act: -0.0000

Data Index: 59983 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.0591. Min Act: -0.0000

Data Index: 522136 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2602. Min Act: -0.0000

Data Index: 453015 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2341. Min Act: -0.0000

Data Index: 1246960 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.3374. Min Act: -0.0000

Data Index: 254991 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.1806. Min Act: -0.0000

Data Index: 622182 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.2900. Min Act: -0.0000

Data Index: 908095 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.0147. Min Act: -0.0000

Data Index: 2472 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.1125. Min Act: -0.0000

Data Index: 958256 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 2.9094. Min Range: -2.9094

Max Act: 2.0983. Min Act: -0.0000

Data Index: 1129759 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 2.9094. Min Range: -2.9094

Max Act: 1.9755. Min Act: -0.0000

Data Index: 919906 (C4 (Web Text))

Max Activating Token Index: 951