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

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

Neuron 3291 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0157. Min Range: -1.0157

Max Act: 1.0157. Min Act: -0.0000

Data Index: 918026 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.9419. Min Act: -0.0000

Data Index: 220942 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8764. Min Act: -0.0000

Data Index: 4598 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1240190 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8597. Min Act: -0.0000

Data Index: 141357 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8363. Min Act: -0.0000

Data Index: 428352 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8401. Min Act: -0.0000

Data Index: 624437 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8364. Min Act: -0.0000

Data Index: 369886 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7832. Min Act: -0.0000

Data Index: 553068 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8165. Min Act: -0.0000

Data Index: 244494 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8102. Min Act: -0.0000

Data Index: 498018 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8240. Min Act: -0.0000

Data Index: 692759 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.8373. Min Act: -0.0000

Data Index: 150002 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7837. Min Act: -0.0000

Data Index: 467710 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7922. Min Act: -0.0000

Data Index: 383780 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7157. Min Act: -0.0000

Data Index: 834184 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7602. Min Act: -0.0000

Data Index: 566643 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7554. Min Act: -0.0000

Data Index: 449087 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7355. Min Act: -0.0000

Data Index: 950801 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.0157. Min Range: -1.0157

Max Act: 0.7699. Min Act: -0.0000

Data Index: 551128 (C4 (Web Text))

Max Activating Token Index: 753