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

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

Neuron 3 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6083. Min Range: -2.6083

Max Act: 2.6083. Min Act: -0.0001

Data Index: 1176117 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 2.6083. Min Range: -2.6083

Max Act: 2.3727. Min Act: -0.0000

Data Index: 310343 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 2.6083. Min Range: -2.6083

Max Act: 2.1159. Min Act: -0.0000

Data Index: 1326893 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.9223. Min Act: -0.0000

Data Index: 1314436 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.8321. Min Act: -0.0001

Data Index: 631063 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.8429. Min Act: -0.0000

Data Index: 113043 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.7513. Min Act: -0.0001

Data Index: 147725 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.8140. Min Act: -0.0000

Data Index: 571764 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.7320. Min Act: -0.0000

Data Index: 871609 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.5917. Min Act: -0.0000

Data Index: 263935 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.7291. Min Act: -0.0001

Data Index: 337274 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1147626 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.5584. Min Act: -0.0001

Data Index: 451902 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.6118. Min Act: -0.0001

Data Index: 7022 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1004919 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.7259. Min Act: -0.0001

Data Index: 616403 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.5713. Min Act: -0.0000

Data Index: 668510 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1145775 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.6267. Min Act: -0.0000

Data Index: 225939 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 2.6083. Min Range: -2.6083

Max Act: 1.6634. Min Act: -0.0001

Data Index: 1194894 (C4 (Web Text))

Max Activating Token Index: 304