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

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

Neuron 4029 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.1075. Min Act: -0.0001

Data Index: 12311 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.1075. Min Range: -1.1075

Max Act: 1.0651. Min Act: -0.0001

Data Index: 96213 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9230. Min Act: -0.0001

Data Index: 493150 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9220. Min Act: -0.0001

Data Index: 718408 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8702. Min Act: -0.0001

Data Index: 66668 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9742. Min Act: -0.0001

Data Index: 260734 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.9379. Min Act: -0.0001

Data Index: 1325676 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1051375 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8024. Min Act: -0.0001

Data Index: 468971 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8364. Min Act: -0.0001

Data Index: 522048 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8519. Min Act: -0.0001

Data Index: 430935 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.7612. Min Act: -0.0001

Data Index: 306484 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8205. Min Act: -0.0001

Data Index: 146250 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1163408 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.8094. Min Act: -0.0001

Data Index: 1078660 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.7719. Min Act: -0.0001

Data Index: 1285691 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.7871. Min Act: -0.0001

Data Index: 1095938 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.7372. Min Act: -0.0001

Data Index: 331747 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1188271 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 1.1075. Min Range: -1.1075

Max Act: 0.7827. Min Act: -0.0001

Data Index: 473894 (C4 (Web Text))

Max Activating Token Index: 919