Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4574 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4134. Min Act: -0.0000

Data Index: 164386 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3553. Min Act: -0.0000

Data Index: 698550 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3502. Min Act: -0.0000

Data Index: 892478 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3405. Min Act: -0.0000

Data Index: 917201 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3247. Min Act: -0.0000

Data Index: 423127 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3084. Min Act: -0.0000

Data Index: 205192 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1422403 (Python Code)

Max Activating Token Index: 857

Text #7

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1068592 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1314747 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3060. Min Act: -0.0000

Data Index: 256366 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3138. Min Act: -0.0000

Data Index: 910319 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3162. Min Act: -0.0000

Data Index: 403800 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2998. Min Act: -0.0000

Data Index: 922953 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2783. Min Act: -0.0000

Data Index: 729832 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2971. Min Act: -0.0000

Data Index: 917447 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2960. Min Act: -0.0000

Data Index: 978313 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3035. Min Act: -0.0000

Data Index: 856933 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2878. Min Act: -0.0000

Data Index: 527149 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1310417 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1207864 (C4 (Web Text))

Max Activating Token Index: 756