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

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

Neuron 1541 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: 1.5227. Min Range: -1.5227

Max Act: 1.5227. Min Act: -0.0001

Data Index: 378145 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.2900. Min Act: -0.0001

Data Index: 61783 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.2327. Min Act: -0.0001

Data Index: 682694 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.3321. Min Act: -0.0001

Data Index: 839078 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.2414. Min Act: -0.0001

Data Index: 1135700 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.1327. Min Act: -0.0002

Data Index: 1015835 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0716. Min Act: -0.0002

Data Index: 460130 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.1122. Min Act: -0.0001

Data Index: 335891 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.1097. Min Act: -0.0002

Data Index: 633007 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.2718. Min Act: -0.0002

Data Index: 571198 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0326. Min Act: -0.0001

Data Index: 32187 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0373. Min Act: -0.0002

Data Index: 624381 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0290. Min Act: -0.0001

Data Index: 870742 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0706. Min Act: -0.0002

Data Index: 57435 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0490. Min Act: -0.0001

Data Index: 1257674 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 1.5227. Min Range: -1.5227

Max Act: 0.9003. Min Act: -0.0002

Data Index: 967155 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.5227. Min Range: -1.5227

Max Act: 1.0480. Min Act: -0.0002

Data Index: 105927 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.5227. Min Range: -1.5227

Max Act: 0.9675. Min Act: -0.0001

Data Index: 480961 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.5227. Min Range: -1.5227

Max Act: 0.9716. Min Act: -0.0001

Data Index: 786749 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.5227. Min Range: -1.5227

Max Act: 0.7964. Min Act: -0.0001

Data Index: 996561 (C4 (Web Text))

Max Activating Token Index: 773