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

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

Neuron 2004 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: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0000

Data Index: 677292 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1078. Min Act: -0.0000

Data Index: 766861 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1120483 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1009. Min Act: -0.0000

Data Index: 346242 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0955. Min Act: -0.0000

Data Index: 816995 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1041487 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0947. Min Act: -0.0001

Data Index: 896256 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0980. Min Act: -0.0001

Data Index: 910725 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0961. Min Act: -0.0000

Data Index: 534430 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0938. Min Act: -0.0001

Data Index: 877815 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0932. Min Act: -0.0000

Data Index: 184379 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0930. Min Act: -0.0000

Data Index: 296576 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0885. Min Act: -0.0000

Data Index: 626643 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0990. Min Act: -0.0000

Data Index: 768716 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0886. Min Act: -0.0001

Data Index: 92678 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0929. Min Act: -0.0000

Data Index: 591247 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0914. Min Act: -0.0000

Data Index: 259932 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0874. Min Act: -0.0000

Data Index: 269451 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0877. Min Act: -0.0000

Data Index: 143286 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0865. Min Act: -0.0000

Data Index: 652192 (C4 (Web Text))

Max Activating Token Index: 433