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

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

Neuron 3977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.4765. Min Act: -0.0001

Data Index: 1311698 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3145. Min Act: -0.0001

Data Index: 948601 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3455. Min Act: -0.0001

Data Index: 105035 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1184939 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3403. Min Act: -0.0001

Data Index: 615797 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1359318 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3072. Min Act: -0.0001

Data Index: 851514 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2842. Min Act: -0.0001

Data Index: 848167 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3028. Min Act: -0.0001

Data Index: 1058549 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2898. Min Act: -0.0001

Data Index: 1115776 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2986. Min Act: -0.0001

Data Index: 317508 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2971. Min Act: -0.0001

Data Index: 477633 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1262686 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2924. Min Act: -0.0001

Data Index: 120695 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2822. Min Act: -0.0001

Data Index: 717920 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2836. Min Act: -0.0001

Data Index: 363926 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2922. Min Act: -0.0001

Data Index: 978009 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2945. Min Act: -0.0001

Data Index: 802949 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1153343 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.4765. Min Range: -0.4765

Max Act: 0.2950. Min Act: -0.0001

Data Index: 193758 (C4 (Web Text))

Max Activating Token Index: 899