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

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

Neuron 3247 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0001

Data Index: 623158 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0997. Min Act: -0.0002

Data Index: 473400 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1036470 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0973. Min Act: -0.0002

Data Index: 651808 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0835. Min Act: -0.0001

Data Index: 386579 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0833. Min Act: -0.0001

Data Index: 242337 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1127594 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0818. Min Act: -0.0002

Data Index: 86882 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0817. Min Act: -0.0002

Data Index: 533873 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0718. Min Act: -0.0001

Data Index: 32844 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0846. Min Act: -0.0001

Data Index: 153873 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0686. Min Act: -0.0001

Data Index: 861858 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0714. Min Act: -0.0001

Data Index: 876778 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0788. Min Act: -0.0001

Data Index: 428761 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1265354 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0727. Min Act: -0.0001

Data Index: 60232 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0716. Min Act: -0.0001

Data Index: 197437 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1353269 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1210660 (C4 (Web Text))

Max Activating Token Index: 856