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

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

Neuron 1841 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: 1.6982. Min Range: -1.6982

Max Act: 1.6384. Min Act: -0.0002

Data Index: 385419 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.6881. Min Act: -0.0002

Data Index: 837378 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5931. Min Act: -0.0001

Data Index: 123075 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5762. Min Act: -0.0002

Data Index: 1205581 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5321. Min Act: -0.0002

Data Index: 681089 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5908. Min Act: -0.0002

Data Index: 845011 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.6982. Min Act: -0.0002

Data Index: 311109 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5525. Min Act: -0.0002

Data Index: 1212823 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.6347. Min Act: -0.0002

Data Index: 550863 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5500. Min Act: -0.0002

Data Index: 778546 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5098. Min Act: -0.0001

Data Index: 486256 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5021. Min Act: -0.0001

Data Index: 883557 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5450. Min Act: -0.0002

Data Index: 630756 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5771. Min Act: -0.0001

Data Index: 732741 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5812. Min Act: -0.0001

Data Index: 1267390 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.4948. Min Act: -0.0002

Data Index: 1287530 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5658. Min Act: -0.0001

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5682. Min Act: -0.0001

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.5243. Min Act: -0.0001

Data Index: 261160 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.6982. Min Range: -1.6982

Max Act: 1.6155. Min Act: -0.0001

Data Index: 703475 (C4 (Web Text))

Max Activating Token Index: 336