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

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

Neuron 1998 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.5060. Min Act: -0.0000

Data Index: 371597 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4436. Min Act: -0.0000

Data Index: 925465 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1088893 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4653. Min Act: -0.0000

Data Index: 382364 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4182. Min Act: -0.0000

Data Index: 184593 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1141208 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3931. Min Act: -0.0000

Data Index: 583325 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4133. Min Act: -0.0000

Data Index: 973825 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1156953 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4010. Min Act: -0.0000

Data Index: 769570 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1087875 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1353950 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4391. Min Act: -0.0000

Data Index: 216282 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3932. Min Act: -0.0000

Data Index: 52504 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1003495 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3992. Min Act: -0.0000

Data Index: 371422 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1237747 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1014956 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1347164 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.5060. Min Range: -0.5060

Max Act: 0.4123. Min Act: -0.0000

Data Index: 859286 (C4 (Web Text))

Max Activating Token Index: 529