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

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

Neuron 603 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: 6.6267. Min Range: -6.6267

Max Act: 6.6267. Min Act: -0.0000

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 6.6267. Min Range: -6.6267

Max Act: 5.8497. Min Act: -0.0000

Data Index: 220183 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 6.6267. Min Range: -6.6267

Max Act: 5.7700. Min Act: -0.0000

Data Index: 658725 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 6.6267. Min Range: -6.6267

Max Act: 5.0039. Min Act: -0.0000

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.9683. Min Act: -0.0000

Data Index: 945319 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 6.6267. Min Range: -6.6267

Max Act: 5.2048. Min Act: -0.0000

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.8070. Min Act: -0.0000

Data Index: 41959 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 6.6267. Min Range: -6.6267

Max Act: 3.9820. Min Act: -0.0000

Data Index: 413859 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.2640. Min Act: -0.0000

Data Index: 1058155 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.4148. Min Act: -0.0000

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.3810. Min Act: -0.0000

Data Index: 730116 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.1255. Min Act: -0.0000

Data Index: 223017 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.4564. Min Act: -0.0000

Data Index: 180360 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.0968. Min Act: -0.0000

Data Index: 1273154 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.2024. Min Act: -0.0000

Data Index: 656746 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.2880. Min Act: -0.0000

Data Index: 1107768 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.0805. Min Act: -0.0000

Data Index: 616486 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 6.6267. Min Range: -6.6267

Max Act: 4.0427. Min Act: -0.0000

Data Index: 592840 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 6.6267. Min Range: -6.6267

Max Act: 3.9814. Min Act: -0.0000

Data Index: 23544 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 6.6267. Min Range: -6.6267

Max Act: 3.6461. Min Act: -0.0000

Data Index: 1349509 (C4 (Web Text))

Max Activating Token Index: 822