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

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

Neuron 438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5012. Min Act: -0.0002

Data Index: 535942 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0002

Data Index: 234521 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4615. Min Act: -0.0002

Data Index: 287311 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4821. Min Act: -0.0002

Data Index: 1052441 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4526. Min Act: -0.0002

Data Index: 368580 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4599. Min Act: -0.0002

Data Index: 1160574 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4111. Min Act: -0.0001

Data Index: 263754 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4297. Min Act: -0.0002

Data Index: 487068 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4016. Min Act: -0.0002

Data Index: 823086 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4431. Min Act: -0.0001

Data Index: 962480 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4356. Min Act: -0.0002

Data Index: 308892 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4063. Min Act: -0.0001

Data Index: 1018901 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3870. Min Act: -0.0002

Data Index: 429234 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4149. Min Act: -0.0001

Data Index: 697514 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3966. Min Act: -0.0002

Data Index: 1263941 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3881. Min Act: -0.0002

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3896. Min Act: -0.0002

Data Index: 404988 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3945. Min Act: -0.0002

Data Index: 849950 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4022. Min Act: -0.0002

Data Index: 679170 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3869. Min Act: -0.0002

Data Index: 98192 (C4 (Web Text))

Max Activating Token Index: 56