Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1100 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1990. Min Range: -2.1990

Max Act: 2.1990. Min Act: -0.0000

Data Index: 155823 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 2.1990. Min Range: -2.1990

Max Act: 2.0659. Min Act: -0.0000

Data Index: 100595 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.7274. Min Act: -0.0000

Data Index: 1207722 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.8101. Min Act: -0.0000

Data Index: 65366 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.6419. Min Act: -0.0000

Data Index: 325230 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.7070. Min Act: -0.0000

Data Index: 480599 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1047607 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.4618. Min Act: -0.0000

Data Index: 135794 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.4613. Min Act: 0.0000

Data Index: 202092 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.3668. Min Act: 0.0000

Data Index: 323969 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.2322. Min Act: -0.0000

Data Index: 261365 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1022819 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.3255. Min Act: -0.0000

Data Index: 918538 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.3140. Min Act: -0.0000

Data Index: 1074968 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.1610. Min Act: -0.0000

Data Index: 408802 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.2224. Min Act: -0.0000

Data Index: 830794 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.1798. Min Act: -0.0000

Data Index: 715021 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.1118. Min Act: -0.0000

Data Index: 364885 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.1128. Min Act: -0.0000

Data Index: 869074 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.1990. Min Range: -2.1990

Max Act: 1.1026. Min Act: -0.0000

Data Index: 570029 (C4 (Web Text))

Max Activating Token Index: 941