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

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

Neuron 2714 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: 0.4902. Min Range: -0.4902

Max Act: 0.4314. Min Act: -0.0001

Data Index: 211035 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4857. Min Act: -0.0000

Data Index: 601101 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4902. Min Act: -0.0000

Data Index: 523108 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1258424 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1186124 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1240153 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4235. Min Act: -0.0001

Data Index: 714222 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4588. Min Act: -0.0000

Data Index: 542352 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4052. Min Act: -0.0001

Data Index: 435620 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4235. Min Act: -0.0001

Data Index: 905090 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1026146 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3949. Min Act: -0.0000

Data Index: 344619 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3943. Min Act: -0.0001

Data Index: 502484 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4149. Min Act: -0.0001

Data Index: 71564 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3747. Min Act: -0.0000

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1109847 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3737. Min Act: -0.0000

Data Index: 236879 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1272078 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3754. Min Act: -0.0001

Data Index: 147749 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3313. Min Act: -0.0000

Data Index: 787202 (C4 (Web Text))

Max Activating Token Index: 155