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

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

Neuron 3958 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3142. Min Range: -2.3142

Max Act: 2.3142. Min Act: -0.0000

Data Index: 305514 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 2.3142. Min Range: -2.3142

Max Act: 1.1155. Min Act: -0.0000

Data Index: 811719 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.8009. Min Act: -0.0000

Data Index: 747101 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5544. Min Act: -0.0000

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5790. Min Act: -0.0000

Data Index: 557833 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5291. Min Act: 0.0000

Data Index: 852650 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.6446. Min Act: -0.0000

Data Index: 361254 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1368676 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1223150 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.4551. Min Act: -0.0000

Data Index: 779600 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5026. Min Act: 0.0000

Data Index: 1350604 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.4018. Min Act: -0.0000

Data Index: 343744 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.4204. Min Act: -0.0000

Data Index: 130252 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.3866. Min Act: -0.0000

Data Index: 990723 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.3912. Min Act: -0.0000

Data Index: 650304 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5039. Min Act: -0.0000

Data Index: 406449 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.5209. Min Act: -0.0000

Data Index: 130944 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.4324. Min Act: 0.0000

Data Index: 138256 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.4437. Min Act: -0.0000

Data Index: 501359 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 2.3142. Min Range: -2.3142

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1305 (C4 (Web Text))

Max Activating Token Index: 951