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

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

Neuron 1912 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: 0.5284. Min Range: -0.5284

Max Act: 0.5171. Min Act: -0.0000

Data Index: 770760 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.5281. Min Act: -0.0000

Data Index: 403877 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.5284. Min Act: -0.0001

Data Index: 193513 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.5185. Min Act: -0.0001

Data Index: 67386 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.5131. Min Act: -0.0001

Data Index: 855632 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4656. Min Act: -0.0000

Data Index: 696633 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4453. Min Act: -0.0001

Data Index: 694725 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4479. Min Act: -0.0000

Data Index: 465961 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4207. Min Act: -0.0001

Data Index: 728126 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4175. Min Act: -0.0001

Data Index: 283036 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4170. Min Act: -0.0000

Data Index: 137333 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4459. Min Act: -0.0000

Data Index: 506914 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1180756 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4070. Min Act: -0.0000

Data Index: 806883 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4310. Min Act: -0.0001

Data Index: 220838 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4327. Min Act: -0.0001

Data Index: 370700 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1176706 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3989. Min Act: -0.0000

Data Index: 967160 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1117258 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3881. Min Act: -0.0001

Data Index: 778188 (C4 (Web Text))

Max Activating Token Index: 167