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

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

Neuron 5070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.4108. Min Act: -0.0000

Data Index: 77387 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1008115 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3931. Min Act: -0.0001

Data Index: 573155 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1108098 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3735. Min Act: -0.0001

Data Index: 595452 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3834. Min Act: -0.0000

Data Index: 401207 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1209997 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1357492 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3833. Min Act: -0.0000

Data Index: 627982 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3640. Min Act: -0.0000

Data Index: 536635 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1239876 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.4000. Min Act: -0.0000

Data Index: 829463 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3658. Min Act: -0.0000

Data Index: 163302 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3808. Min Act: -0.0000

Data Index: 21963 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1654563 (Python Code)

Max Activating Token Index: 802

Text #15

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3173. Min Act: -0.0000

Data Index: 830863 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3582. Min Act: -0.0001

Data Index: 791170 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3506. Min Act: -0.0000

Data Index: 538138 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3482. Min Act: -0.0000

Data Index: 582071 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.4108. Min Range: -0.4108

Max Act: 0.3428. Min Act: -0.0000

Data Index: 170816 (C4 (Web Text))

Max Activating Token Index: 687