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

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

Neuron 3943 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6128. Min Range: -2.6128

Max Act: 2.6128. Min Act: -0.0000

Data Index: 830547 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 2.6128. Min Range: -2.6128

Max Act: 2.3039. Min Act: -0.0000

Data Index: 605413 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 2.6128. Min Range: -2.6128

Max Act: 2.3666. Min Act: -0.0000

Data Index: 873036 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 2.6128. Min Range: -2.6128

Max Act: 2.4142. Min Act: -0.0000

Data Index: 111614 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 2.6128. Min Range: -2.6128

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1164931 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 2.6128. Min Range: -2.6128

Max Act: 2.0039. Min Act: -0.0000

Data Index: 245062 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.9819. Min Act: -0.0000

Data Index: 954541 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1177414 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.9754. Min Act: -0.0000

Data Index: 577707 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.9817. Min Act: -0.0000

Data Index: 122974 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1088697 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.9390. Min Act: -0.0000

Data Index: 511686 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.8098. Min Act: -0.0000

Data Index: 313007 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.8697. Min Act: -0.0000

Data Index: 785089 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.8618. Min Act: -0.0000

Data Index: 1024345 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.8459. Min Act: -0.0000

Data Index: 587645 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.7467. Min Act: -0.0000

Data Index: 1016501 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.7452. Min Act: -0.0000

Data Index: 358900 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.8174. Min Act: -0.0000

Data Index: 929140 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 2.6128. Min Range: -2.6128

Max Act: 1.7182. Min Act: -0.0000

Data Index: 711444 (C4 (Web Text))

Max Activating Token Index: 820