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

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

Neuron 4714 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: 3.4653. Min Range: -3.4653

Max Act: 3.4011. Min Act: 0.0001

Data Index: 949709 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 3.4653. Min Range: -3.4653

Max Act: 3.4653. Min Act: 0.0000

Data Index: 1217659 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.4653. Min Range: -3.4653

Max Act: 3.1246. Min Act: 0.0000

Data Index: 311821 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.9301. Min Act: 0.0001

Data Index: 928968 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.7312. Min Act: -0.0000

Data Index: 726789 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.4960. Min Act: -0.0000

Data Index: 455946 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.4623. Min Act: -0.0000

Data Index: 678299 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.4655. Min Act: 0.0000

Data Index: 1230220 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.4626. Min Act: 0.0000

Data Index: 498936 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.3784. Min Act: 0.0002

Data Index: 950796 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.4890. Min Act: 0.0000

Data Index: 336531 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.3042. Min Act: 0.0000

Data Index: 79372 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.3010. Min Act: 0.0000

Data Index: 212226 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.2841. Min Act: 0.0000

Data Index: 244207 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.2566. Min Act: -0.0000

Data Index: 1297358 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.2515. Min Act: -0.0000

Data Index: 997211 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.3575. Min Act: 0.0000

Data Index: 1032324 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.1054. Min Act: -0.0000

Data Index: 479453 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.2331. Min Act: -0.0000

Data Index: 1039122 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.4653. Min Range: -3.4653

Max Act: 2.2016. Min Act: 0.0000

Data Index: 1163859 (C4 (Web Text))

Max Activating Token Index: 39