Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.2534. Min Act: -0.0000

Data Index: 82806 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.2734. Min Act: -0.0000

Data Index: 144657 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.2609. Min Act: -0.0000

Data Index: 1056229 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.1448. Min Act: -0.0000

Data Index: 133855 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.1227. Min Act: -0.0000

Data Index: 963243 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.0707. Min Act: -0.0000

Data Index: 1229811 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.9659. Min Act: -0.0000

Data Index: 274311 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.0133. Min Act: -0.0000

Data Index: 495592 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 2.2734. Min Range: -2.2734

Max Act: 2.1022. Min Act: -0.0000

Data Index: 30389 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.8675. Min Act: -0.0000

Data Index: 1004910 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.9566. Min Act: -0.0000

Data Index: 1316850 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.9140. Min Act: -0.0000

Data Index: 924871 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.7569. Min Act: -0.0000

Data Index: 950595 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.7483. Min Act: -0.0000

Data Index: 177157 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.8330. Min Act: -0.0000

Data Index: 212838 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.8281. Min Act: -0.0000

Data Index: 658468 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.8337. Min Act: -0.0000

Data Index: 502602 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.7906. Min Act: -0.0000

Data Index: 288179 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.7780. Min Act: -0.0000

Data Index: 230879 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 2.2734. Min Range: -2.2734

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1019327 (C4 (Web Text))

Max Activating Token Index: 187