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

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

Neuron 3008 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1371. Min Range: -5.1371

Max Act: 5.1371. Min Act: -0.0000

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 5.1371. Min Range: -5.1371

Max Act: 4.2269. Min Act: -0.0000

Data Index: 663610 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.9031. Min Act: -0.0000

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.8076. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.7327. Min Act: -0.0000

Data Index: 988914 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.2778. Min Act: -0.0000

Data Index: 786237 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.5238. Min Act: -0.0000

Data Index: 412912 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3357. Min Act: -0.0000

Data Index: 1017291 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3214. Min Act: -0.0000

Data Index: 893336 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.4524. Min Act: -0.0000

Data Index: 899158 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.2922. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3035. Min Act: -0.0000

Data Index: 50230 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.2712. Min Act: -0.0000

Data Index: 1408169 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.2478. Min Act: -0.0000

Data Index: 345334 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.2737. Min Act: -0.0000

Data Index: 973915 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3911. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.4254. Min Act: -0.0000

Data Index: 1140632 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3835. Min Act: -0.0000

Data Index: 1082014 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3299. Min Act: -0.0000

Data Index: 1369237 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 5.1371. Min Range: -5.1371

Max Act: 3.3347. Min Act: -0.0000

Data Index: 1600376 (Python Code)

Max Activating Token Index: 798