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

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

Neuron 970 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.7647. Min Act: -0.0001

Data Index: 1151378 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6418. Min Act: -0.0001

Data Index: 161556 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6603. Min Act: -0.0001

Data Index: 944857 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.8110. Min Act: -0.0001

Data Index: 685311 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6297. Min Act: -0.0001

Data Index: 852281 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6585. Min Act: -0.0001

Data Index: 126839 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6516. Min Act: -0.0001

Data Index: 767558 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6728. Min Act: -0.0001

Data Index: 9846 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.7291. Min Act: -0.0001

Data Index: 495610 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6140. Min Act: -0.0001

Data Index: 1349006 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1091556 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6747. Min Act: -0.0001

Data Index: 636045 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.5794. Min Act: -0.0001

Data Index: 514356 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1190375 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.5916. Min Act: -0.0001

Data Index: 232343 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6832. Min Act: -0.0001

Data Index: 1262111 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.6018. Min Act: -0.0001

Data Index: 339218 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.5980. Min Act: -0.0001

Data Index: 954127 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1187323 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.8110. Min Range: -0.8110

Max Act: 0.5348. Min Act: -0.0001

Data Index: 950088 (C4 (Web Text))

Max Activating Token Index: 184