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

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

Neuron 1252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3969. Min Act: -0.0001

Data Index: 350030 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.4246. Min Act: -0.0000

Data Index: 363766 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3689. Min Act: -0.0001

Data Index: 1099930 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3382. Min Act: -0.0001

Data Index: 980034 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3122. Min Act: -0.0001

Data Index: 57445 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3266. Min Act: -0.0001

Data Index: 155306 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3013. Min Act: -0.0001

Data Index: 44778 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3000. Min Act: -0.0001

Data Index: 346173 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1202219 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3048. Min Act: -0.0001

Data Index: 596495 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1342482 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3000. Min Act: -0.0001

Data Index: 292432 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2799. Min Act: -0.0001

Data Index: 1341476 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2987. Min Act: -0.0001

Data Index: 48535 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2994. Min Act: -0.0001

Data Index: 883461 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2983. Min Act: -0.0001

Data Index: 614313 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1019067 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2879. Min Act: -0.0001

Data Index: 694503 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2912. Min Act: -0.0001

Data Index: 420708 (C4 (Web Text))

Max Activating Token Index: 114