Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1097 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.7213. Min Act: -0.0001

Data Index: 450893 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6991. Min Act: -0.0001

Data Index: 1083672 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6151. Min Act: -0.0001

Data Index: 1141732 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6564. Min Act: -0.0001

Data Index: 844827 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.7199. Min Act: -0.0001

Data Index: 904501 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6138. Min Act: -0.0001

Data Index: 11380 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6588. Min Act: -0.0001

Data Index: 954986 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5937. Min Act: -0.0001

Data Index: 500884 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4562. Min Act: -0.0001

Data Index: 1048021 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1321372 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5948. Min Act: -0.0001

Data Index: 267160 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1232651 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5853. Min Act: -0.0001

Data Index: 84286 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5616. Min Act: -0.0001

Data Index: 218062 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5480. Min Act: -0.0001

Data Index: 54656 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6013. Min Act: -0.0001

Data Index: 1149811 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5599. Min Act: -0.0001

Data Index: 704588 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5949. Min Act: -0.0001

Data Index: 718340 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5545. Min Act: -0.0001

Data Index: 446275 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5384. Min Act: -0.0001

Data Index: 387925 (C4 (Web Text))

Max Activating Token Index: 732