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

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

Neuron 2822 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: 1.1089. Min Range: -1.1089

Max Act: 1.1089. Min Act: -0.0000

Data Index: 371853 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1070473 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.8405. Min Act: -0.0000

Data Index: 247397 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.8514. Min Act: -0.0001

Data Index: 500817 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7661. Min Act: -0.0000

Data Index: 202432 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7829. Min Act: -0.0000

Data Index: 278942 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7560. Min Act: -0.0000

Data Index: 468957 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7652. Min Act: -0.0001

Data Index: 711921 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7001. Min Act: -0.0001

Data Index: 1149916 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7401. Min Act: -0.0000

Data Index: 753679 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1284874 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6868. Min Act: -0.0000

Data Index: 402082 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6808. Min Act: -0.0000

Data Index: 25247 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6791. Min Act: -0.0000

Data Index: 539975 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6807. Min Act: -0.0000

Data Index: 132271 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1145937 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6722. Min Act: -0.0000

Data Index: 998440 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6928. Min Act: -0.0001

Data Index: 1153566 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6897. Min Act: -0.0000

Data Index: 606189 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.1089. Min Range: -1.1089

Max Act: 0.6608. Min Act: -0.0000

Data Index: 181431 (C4 (Web Text))

Max Activating Token Index: 12