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

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

Neuron 2933 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.0590. Min Act: -0.0000

Data Index: 880736 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.6842. Min Range: -1.6842

Max Act: 1.6842. Min Act: -0.0000

Data Index: 94661 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.3327. Min Act: -0.0001

Data Index: 833887 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.3582. Min Act: -0.0001

Data Index: 165259 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2867. Min Act: -0.0001

Data Index: 934814 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1493304 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2328. Min Act: -0.0000

Data Index: 756382 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2511. Min Act: -0.0001

Data Index: 569976 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2488. Min Act: -0.0001

Data Index: 240057 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1028532 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1913. Min Act: -0.0001

Data Index: 328827 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2016. Min Act: -0.0000

Data Index: 764686 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1952. Min Act: -0.0001

Data Index: 483320 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1414378 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2027. Min Act: -0.0001

Data Index: 326923 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1540798 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1889. Min Act: -0.0001

Data Index: 716424 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1886. Min Act: -0.0001

Data Index: 719703 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.6842. Min Range: -1.6842

Max Act: 0.1564. Min Act: -0.0001

Data Index: 592569 (C4 (Web Text))

Max Activating Token Index: 844