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

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

Neuron 1376 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: 0.8462. Min Range: -0.8462

Max Act: 0.8462. Min Act: -0.0000

Data Index: 604499 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.6168. Min Act: -0.0000

Data Index: 624717 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.5948. Min Act: -0.0000

Data Index: 82361 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.5427. Min Act: -0.0001

Data Index: 692175 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.6002. Min Act: -0.0000

Data Index: 689401 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.5262. Min Act: -0.0000

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1228345 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.4595. Min Act: -0.0000

Data Index: 728977 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1095430 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.4515. Min Act: -0.0000

Data Index: 240762 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.4127. Min Act: -0.0000

Data Index: 205001 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3695. Min Act: -0.0000

Data Index: 471881 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3813. Min Act: -0.0001

Data Index: 87336 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.4051. Min Act: -0.0001

Data Index: 855487 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3981. Min Act: -0.0000

Data Index: 748184 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3846. Min Act: -0.0000

Data Index: 300892 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3823. Min Act: -0.0000

Data Index: 949297 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3873. Min Act: -0.0001

Data Index: 795628 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.8462. Min Range: -0.8462

Max Act: 0.3744. Min Act: -0.0000

Data Index: 730235 (C4 (Web Text))

Max Activating Token Index: 589