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

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

Neuron 2422 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: 1.5670. Min Range: -1.5670

Max Act: 1.4960. Min Act: -0.0001

Data Index: 1049676 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5558. Min Act: -0.0001

Data Index: 422339 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.4775. Min Act: -0.0001

Data Index: 273629 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5670. Min Act: -0.0001

Data Index: 716110 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1223740 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.4340. Min Act: -0.0001

Data Index: 9712 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.3981. Min Act: -0.0001

Data Index: 570371 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.3301. Min Act: -0.0001

Data Index: 99361 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2725. Min Act: -0.0001

Data Index: 885158 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2179. Min Act: -0.0001

Data Index: 968966 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2043. Min Act: -0.0001

Data Index: 1190596 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.3017. Min Act: -0.0001

Data Index: 360152 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.1871. Min Act: -0.0001

Data Index: 375506 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2131. Min Act: -0.0001

Data Index: 403379 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2138. Min Act: -0.0001

Data Index: 973563 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2442. Min Act: -0.0001

Data Index: 246397 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.1529. Min Act: -0.0001

Data Index: 90225 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.1845. Min Act: -0.0001

Data Index: 195407 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.2435. Min Act: -0.0001

Data Index: 468093 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.1507. Min Act: -0.0001

Data Index: 518069 (C4 (Web Text))

Max Activating Token Index: 965