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

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

Neuron 689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3886. Min Act: -0.0003

Data Index: 602002 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3518. Min Act: -0.0003

Data Index: 1087420 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3359. Min Act: -0.0003

Data Index: 1005151 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3358. Min Act: -0.0003

Data Index: 98454 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3206. Min Act: -0.0003

Data Index: 1173211 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3386. Min Act: -0.0003

Data Index: 1297109 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3215. Min Act: -0.0003

Data Index: 1237259 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3276. Min Act: -0.0003

Data Index: 513745 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3259. Min Act: -0.0003

Data Index: 1074322 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3110. Min Act: -0.0003

Data Index: 244534 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3093. Min Act: -0.0003

Data Index: 505905 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3072. Min Act: -0.0003

Data Index: 1039857 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3066. Min Act: -0.0003

Data Index: 406149 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3142. Min Act: -0.0003

Data Index: 230859 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.3014. Min Act: -0.0003

Data Index: 1003339 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2984. Min Act: -0.0003

Data Index: 1268455 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2977. Min Act: -0.0003

Data Index: 1353645 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2855. Min Act: -0.0003

Data Index: 401083 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2947. Min Act: -0.0003

Data Index: 55479 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.3886. Min Range: -0.3886

Max Act: 0.2921. Min Act: -0.0003

Data Index: 734008 (C4 (Web Text))

Max Activating Token Index: 476