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

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

Neuron 1380 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5270. Min Act: -0.0000

Data Index: 540487 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1183048 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4892. Min Act: 0.0000

Data Index: 699161 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1313206 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4504. Min Act: -0.0000

Data Index: 871253 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4564. Min Act: -0.0001

Data Index: 429870 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4547. Min Act: -0.0001

Data Index: 302470 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1266718 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4495. Min Act: -0.0000

Data Index: 709232 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4389. Min Act: -0.0000

Data Index: 776882 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1254829 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4279. Min Act: -0.0000

Data Index: 139906 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1044609 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4273. Min Act: -0.0000

Data Index: 173563 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4080. Min Act: -0.0000

Data Index: 820837 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4036. Min Act: -0.0001

Data Index: 721237 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1277128 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3840. Min Act: -0.0000

Data Index: 708637 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3878. Min Act: -0.0000

Data Index: 215782 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1323677 (C4 (Web Text))

Max Activating Token Index: 31