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

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

Neuron 2780 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.5291. Min Act: -0.0000

Data Index: 660924 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.5028. Min Act: -0.0000

Data Index: 1190354 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.4831. Min Act: -0.0000

Data Index: 885431 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.2968. Min Act: -0.0000

Data Index: 104114 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.0779. Min Act: -0.0000

Data Index: 197211 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.2902. Min Act: -0.0000

Data Index: 577756 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.0021. Min Act: -0.0000

Data Index: 1217337 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.1159. Min Act: -0.0000

Data Index: 1123438 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.1144. Min Act: -0.0000

Data Index: 820723 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 5.5291. Min Range: -5.5291

Max Act: 5.0924. Min Act: -0.0000

Data Index: 382479 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.8936. Min Act: -0.0000

Data Index: 386799 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.9264. Min Act: -0.0000

Data Index: 850739 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.8772. Min Act: -0.0000

Data Index: 1253138 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.6597. Min Act: -0.0000

Data Index: 863055 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.8676. Min Act: -0.0000

Data Index: 889996 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.7928. Min Act: -0.0000

Data Index: 995048 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.7661. Min Act: -0.0000

Data Index: 781021 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.9345. Min Act: -0.0000

Data Index: 770478 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.7316. Min Act: -0.0000

Data Index: 1093612 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 5.5291. Min Range: -5.5291

Max Act: 4.9400. Min Act: -0.0000

Data Index: 186860 (C4 (Web Text))

Max Activating Token Index: 636