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

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

Neuron 2923 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.3416. Min Act: -0.0000

Data Index: 961225 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.2230. Min Act: -0.0000

Data Index: 259565 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1226275 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1174158 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1324736 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0369. Min Act: -0.0000

Data Index: 338654 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0328. Min Act: -0.0000

Data Index: 57052 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1312772 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0264. Min Act: -0.0000

Data Index: 47991 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0719. Min Act: -0.0000

Data Index: 641197 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9841. Min Act: -0.0000

Data Index: 568289 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9674. Min Act: -0.0000

Data Index: 854607 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.3416. Min Range: -1.3416

Max Act: 1.0565. Min Act: -0.0000

Data Index: 997865 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9676. Min Act: -0.0000

Data Index: 891030 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1225896 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.8696. Min Act: -0.0000

Data Index: 541405 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1174689 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9133. Min Act: -0.0000

Data Index: 319541 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9346. Min Act: -0.0000

Data Index: 897489 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.3416. Min Range: -1.3416

Max Act: 0.9260. Min Act: -0.0000

Data Index: 704449 (C4 (Web Text))

Max Activating Token Index: 908