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

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

Neuron 2208 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: 0.5861. Min Range: -0.5861

Max Act: 0.5861. Min Act: -0.0000

Data Index: 713839 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4845. Min Act: -0.0000

Data Index: 644059 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1161503 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4560. Min Act: -0.0000

Data Index: 771541 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4706. Min Act: -0.0000

Data Index: 713389 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1014732 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4692. Min Act: -0.0000

Data Index: 766370 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4879. Min Act: -0.0000

Data Index: 42337 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4506. Min Act: -0.0000

Data Index: 913029 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1259013 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.5184. Min Act: -0.0000

Data Index: 107279 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4299. Min Act: -0.0000

Data Index: 708778 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4370. Min Act: -0.0000

Data Index: 638730 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.4190. Min Act: -0.0000

Data Index: 832892 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3963. Min Act: -0.0000

Data Index: 465951 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3576. Min Act: -0.0000

Data Index: 314442 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3759. Min Act: -0.0000

Data Index: 827762 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1069221 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3503. Min Act: -0.0000

Data Index: 798138 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.5861. Min Range: -0.5861

Max Act: 0.3901. Min Act: -0.0000

Data Index: 507916 (C4 (Web Text))

Max Activating Token Index: 598