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

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

Neuron 3140 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: 0.7161. Min Range: -0.7161

Max Act: 0.6879. Min Act: 0.0002

Data Index: 180756 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6799. Min Act: -0.0000

Data Index: 555176 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.7161. Min Act: -0.0000

Data Index: 124841 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6137. Min Act: 0.0001

Data Index: 629542 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6142. Min Act: -0.0000

Data Index: 335375 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6076. Min Act: -0.0000

Data Index: 826383 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1308711 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1351350 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5757. Min Act: 0.0002

Data Index: 575105 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5739. Min Act: 0.0000

Data Index: 577888 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1012894 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5711. Min Act: -0.0000

Data Index: 969783 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1204479 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5891. Min Act: 0.0000

Data Index: 1286214 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5645. Min Act: -0.0000

Data Index: 416962 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5853. Min Act: -0.0000

Data Index: 786877 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5725. Min Act: 0.0000

Data Index: 265155 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1184285 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5728. Min Act: 0.0000

Data Index: 698464 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5548. Min Act: -0.0000

Data Index: 999021 (C4 (Web Text))

Max Activating Token Index: 692