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

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

Neuron 240 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: 0.8188. Min Range: -0.8188

Max Act: 0.8188. Min Act: -0.0001

Data Index: 1044967 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.8134. Min Act: -0.0001

Data Index: 485070 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.8055. Min Act: -0.0001

Data Index: 581958 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7592. Min Act: -0.0001

Data Index: 1222263 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7082. Min Act: -0.0001

Data Index: 412790 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1148735 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7153. Min Act: -0.0001

Data Index: 370773 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1035377 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6931. Min Act: -0.0001

Data Index: 832641 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7436. Min Act: -0.0001

Data Index: 618955 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6669. Min Act: -0.0001

Data Index: 567096 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6888. Min Act: -0.0001

Data Index: 85197 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7055. Min Act: -0.0001

Data Index: 750744 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7244. Min Act: -0.0001

Data Index: 309591 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7031. Min Act: -0.0001

Data Index: 542421 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6993. Min Act: -0.0001

Data Index: 417353 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1072242 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6754. Min Act: -0.0001

Data Index: 162075 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6714. Min Act: -0.0001

Data Index: 978902 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6688. Min Act: -0.0001

Data Index: 723347 (C4 (Web Text))

Max Activating Token Index: 427