Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.1209. Min Act: -0.0000

Data Index: 245158 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0731. Min Act: -0.0000

Data Index: 747699 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.1209. Min Range: -1.1209

Max Act: 1.0634. Min Act: -0.0000

Data Index: 160023 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9650. Min Act: -0.0000

Data Index: 97334 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9553. Min Act: -0.0000

Data Index: 235050 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9795. Min Act: -0.0000

Data Index: 44462 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9396. Min Act: -0.0000

Data Index: 802922 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8792. Min Act: -0.0000

Data Index: 835948 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1273454 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9068. Min Act: -0.0001

Data Index: 1138847 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1196825 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8245. Min Act: -0.0000

Data Index: 400978 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8954. Min Act: -0.0001

Data Index: 864602 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9300. Min Act: -0.0000

Data Index: 104949 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1280466 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.9426. Min Act: -0.0000

Data Index: 306253 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1242788 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8619. Min Act: -0.0000

Data Index: 237881 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8542. Min Act: -0.0000

Data Index: 576283 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.1209. Min Range: -1.1209

Max Act: 0.8295. Min Act: -0.0000

Data Index: 946678 (C4 (Web Text))

Max Activating Token Index: 178