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

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

Neuron 3016 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: 1.2314. Min Range: -1.2314

Max Act: 1.2314. Min Act: -0.0000

Data Index: 524577 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.2314. Min Range: -1.2314

Max Act: 1.0137. Min Act: -0.0000

Data Index: 214029 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.9947. Min Act: -0.0000

Data Index: 121682 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.9552. Min Act: -0.0000

Data Index: 464966 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.9422. Min Act: -0.0000

Data Index: 323947 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.9908. Min Act: -0.0000

Data Index: 940809 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.9184. Min Act: -0.0000

Data Index: 543473 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1258698 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8896. Min Act: -0.0000

Data Index: 332053 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1129190 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8824. Min Act: -0.0000

Data Index: 163859 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1249656 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8481. Min Act: -0.0000

Data Index: 132416 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8062. Min Act: -0.0000

Data Index: 890831 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.7904. Min Act: -0.0000

Data Index: 65395 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8163. Min Act: -0.0000

Data Index: 255543 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8432. Min Act: -0.0000

Data Index: 701090 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.8273. Min Act: 0.0000

Data Index: 774172 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1164904 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.2314. Min Range: -1.2314

Max Act: 0.7831. Min Act: -0.0000

Data Index: 286732 (C4 (Web Text))

Max Activating Token Index: 164