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

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

Neuron 2734 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: 0.8382. Min Range: -0.8382

Max Act: 0.8340. Min Act: -0.0001

Data Index: 967948 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.8382. Min Act: -0.0001

Data Index: 288952 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.8167. Min Act: -0.0001

Data Index: 968124 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7606. Min Act: -0.0002

Data Index: 296084 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7479. Min Act: -0.0001

Data Index: 1198845 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7478. Min Act: -0.0002

Data Index: 472443 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7235. Min Act: -0.0001

Data Index: 820678 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1024910 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7368. Min Act: -0.0002

Data Index: 852305 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7278. Min Act: -0.0002

Data Index: 127493 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7111. Min Act: -0.0001

Data Index: 971187 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6997. Min Act: -0.0002

Data Index: 639916 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7207. Min Act: -0.0002

Data Index: 707352 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7365. Min Act: -0.0002

Data Index: 775058 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7046. Min Act: -0.0002

Data Index: 826052 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6672. Min Act: -0.0001

Data Index: 776585 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7016. Min Act: -0.0001

Data Index: 318526 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6593. Min Act: -0.0001

Data Index: 569255 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7280. Min Act: -0.0002

Data Index: 1147340 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1061425 (C4 (Web Text))

Max Activating Token Index: 984