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

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

Neuron 2898 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: 0.6184. Min Range: -0.6184

Max Act: 0.6184. Min Act: -0.0001

Data Index: 116572 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1115899 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.6008. Min Act: 0.0001

Data Index: 601866 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1329145 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5594. Min Act: 0.0001

Data Index: 959318 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5417. Min Act: -0.0000

Data Index: 418102 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5843. Min Act: -0.0000

Data Index: 550262 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5474. Min Act: -0.0000

Data Index: 558995 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5449. Min Act: -0.0000

Data Index: 716355 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5565. Min Act: -0.0000

Data Index: 81811 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5431. Min Act: -0.0000

Data Index: 331314 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1065307 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5016. Min Act: -0.0000

Data Index: 937681 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.5269. Min Act: -0.0001

Data Index: 1344705 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4716. Min Act: 0.0001

Data Index: 427415 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4704. Min Act: -0.0000

Data Index: 65951 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4978. Min Act: -0.0001

Data Index: 336944 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4961. Min Act: -0.0000

Data Index: 577032 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4804. Min Act: -0.0000

Data Index: 393575 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.6184. Min Range: -0.6184

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1314483 (C4 (Web Text))

Max Activating Token Index: 695