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

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

Neuron 3052 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3059. Min Range: -4.3059

Max Act: 4.3059. Min Act: -0.0000

Data Index: 1014886 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 4.3059. Min Range: -4.3059

Max Act: 4.2957. Min Act: -0.0000

Data Index: 1241451 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 4.3059. Min Range: -4.3059

Max Act: 3.9932. Min Act: -0.0000

Data Index: 382769 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 4.3059. Min Range: -4.3059

Max Act: 3.8446. Min Act: -0.0000

Data Index: 556025 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 4.3059. Min Range: -4.3059

Max Act: 4.1448. Min Act: -0.0000

Data Index: 901329 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 4.3059. Min Range: -4.3059

Max Act: 3.9554. Min Act: -0.0000

Data Index: 1170028 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 4.3059. Min Range: -4.3059

Max Act: 3.9342. Min Act: -0.0000

Data Index: 1158838 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 4.3059. Min Range: -4.3059

Max Act: 3.7827. Min Act: -0.0000

Data Index: 871915 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 4.3059. Min Range: -4.3059

Max Act: 3.7695. Min Act: -0.0000

Data Index: 190285 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.6828. Min Act: -0.0000

Data Index: 875943 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.5596. Min Act: -0.0000

Data Index: 159267 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.4994. Min Act: -0.0000

Data Index: 607232 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.5664. Min Act: -0.0000

Data Index: 1254188 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.2832. Min Act: -0.0000

Data Index: 950293 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.1486. Min Act: -0.0000

Data Index: 164513 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 4.3059. Min Range: -4.3059

Max Act: 1.8792. Min Act: -0.0000

Data Index: 533827 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 4.3059. Min Range: -4.3059

Max Act: 1.9070. Min Act: -0.0000

Data Index: 561852 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 4.3059. Min Range: -4.3059

Max Act: 1.9346. Min Act: -0.0000

Data Index: 673854 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 4.3059. Min Range: -4.3059

Max Act: 2.0345. Min Act: -0.0000

Data Index: 203772 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 4.3059. Min Range: -4.3059

Max Act: 1.9745. Min Act: -0.0000

Data Index: 321145 (C4 (Web Text))

Max Activating Token Index: 1019