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

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

Neuron 2130 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: 0.4713. Min Range: -0.4713

Max Act: 0.4713. Min Act: -0.0001

Data Index: 808508 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4412. Min Act: -0.0002

Data Index: 329931 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4132. Min Act: -0.0002

Data Index: 885532 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4264. Min Act: -0.0002

Data Index: 107325 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4336. Min Act: -0.0002

Data Index: 1207410 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4030. Min Act: -0.0002

Data Index: 212274 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3860. Min Act: -0.0002

Data Index: 529536 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3846. Min Act: -0.0002

Data Index: 594849 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3952. Min Act: -0.0002

Data Index: 1129340 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3954. Min Act: -0.0002

Data Index: 965352 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3901. Min Act: -0.0001

Data Index: 730734 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3596. Min Act: -0.0002

Data Index: 473288 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3593. Min Act: -0.0002

Data Index: 575137 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3485. Min Act: -0.0002

Data Index: 9851 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3485. Min Act: -0.0002

Data Index: 879483 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3793. Min Act: -0.0002

Data Index: 1001667 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3815. Min Act: -0.0002

Data Index: 132163 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3807. Min Act: -0.0002

Data Index: 286223 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3667. Min Act: -0.0002

Data Index: 917409 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3622. Min Act: -0.0002

Data Index: 1090979 (C4 (Web Text))

Max Activating Token Index: 560