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

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

Neuron 3924 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0972. Min Act: -0.0001

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0628. Min Act: -0.0001

Data Index: 66490 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0554. Min Act: -0.0001

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0129. Min Act: -0.0002

Data Index: 656354 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0135. Min Act: -0.0002

Data Index: 1096916 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9636. Min Act: -0.0001

Data Index: 930353 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9377. Min Act: -0.0002

Data Index: 846050 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9481. Min Act: -0.0001

Data Index: 533750 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9702. Min Act: -0.0001

Data Index: 136825 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8869. Min Act: -0.0001

Data Index: 976508 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9077. Min Act: -0.0001

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9294. Min Act: -0.0001

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9332. Min Act: -0.0002

Data Index: 662091 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9502. Min Act: -0.0001

Data Index: 992962 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9746. Min Act: -0.0002

Data Index: 19083 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8951. Min Act: -0.0001

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9178. Min Act: -0.0001

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8893. Min Act: -0.0001

Data Index: 1346781 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9117. Min Act: -0.0001

Data Index: 260731 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9261. Min Act: -0.0001

Data Index: 159064 (C4 (Web Text))

Max Activating Token Index: 567