Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1752 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.8870. Min Act: -0.0001

Data Index: 971725 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7317. Min Act: -0.0001

Data Index: 903527 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1124596 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6969. Min Act: -0.0001

Data Index: 982831 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1104644 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6664. Min Act: -0.0001

Data Index: 734804 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6401. Min Act: -0.0001

Data Index: 597699 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6346. Min Act: -0.0001

Data Index: 464909 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6360. Min Act: -0.0001

Data Index: 1143030 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6964. Min Act: -0.0001

Data Index: 696138 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6290. Min Act: -0.0001

Data Index: 700370 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6535. Min Act: -0.0001

Data Index: 1225082 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6201. Min Act: -0.0001

Data Index: 1206784 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6195. Min Act: -0.0001

Data Index: 638252 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6290. Min Act: -0.0001

Data Index: 931134 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6082. Min Act: -0.0001

Data Index: 890682 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5623. Min Act: -0.0001

Data Index: 933395 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5284. Min Act: -0.0001

Data Index: 949260 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.6038. Min Act: -0.0001

Data Index: 559316 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.8870. Min Range: -0.8870

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1036024 (C4 (Web Text))

Max Activating Token Index: 381