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

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

Neuron 1641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1906. Min Act: -0.0002

Data Index: 831654 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.2530. Min Act: -0.0002

Data Index: 572423 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.2097. Min Act: -0.0001

Data Index: 1122073 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9808. Min Act: -0.0001

Data Index: 1318198 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0634. Min Act: -0.0002

Data Index: 338706 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0856. Min Act: -0.0001

Data Index: 470162 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9844. Min Act: -0.0002

Data Index: 862304 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0596. Min Act: -0.0001

Data Index: 151169 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0699. Min Act: -0.0001

Data Index: 420593 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.1820. Min Act: -0.0001

Data Index: 585689 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9425. Min Act: -0.0001

Data Index: 419835 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0643. Min Act: -0.0002

Data Index: 502234 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9490. Min Act: -0.0001

Data Index: 292148 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0117. Min Act: -0.0001

Data Index: 1252907 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1205209 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0238. Min Act: -0.0001

Data Index: 1314833 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.2530. Min Range: -1.2530

Max Act: 1.0041. Min Act: -0.0001

Data Index: 1266946 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9913. Min Act: -0.0001

Data Index: 250613 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9828. Min Act: -0.0002

Data Index: 1220241 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.2530. Min Range: -1.2530

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1182720 (C4 (Web Text))

Max Activating Token Index: 918