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

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

Neuron 1414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2381. Min Act: -0.0000

Data Index: 790920 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2362. Min Act: -0.0000

Data Index: 207223 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2228. Min Act: -0.0000

Data Index: 462500 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2097. Min Act: -0.0001

Data Index: 759826 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2098. Min Act: -0.0001

Data Index: 267957 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1085622 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1201658 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2143. Min Act: -0.0000

Data Index: 737844 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2039. Min Act: -0.0000

Data Index: 347443 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2014. Min Act: -0.0001

Data Index: 154230 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1920. Min Act: -0.0000

Data Index: 247863 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2115. Min Act: -0.0001

Data Index: 834619 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2028. Min Act: -0.0001

Data Index: 303710 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1303566 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1941. Min Act: -0.0001

Data Index: 353549 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1975. Min Act: -0.0001

Data Index: 401271 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1952. Min Act: -0.0001

Data Index: 691864 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1900. Min Act: -0.0000

Data Index: 182690 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1951. Min Act: -0.0001

Data Index: 977053 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1941. Min Act: -0.0001

Data Index: 763802 (C4 (Web Text))

Max Activating Token Index: 128