Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 804 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1096556 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0911. Min Act: -0.0003

Data Index: 503425 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0003

Data Index: 1309006 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1359263 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0883. Min Act: -0.0003

Data Index: 384409 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0857. Min Act: -0.0002

Data Index: 161948 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0846. Min Act: -0.0003

Data Index: 874674 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0809. Min Act: -0.0003

Data Index: 275047 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0752. Min Act: -0.0003

Data Index: 124285 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0778. Min Act: -0.0003

Data Index: 49043 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0775. Min Act: -0.0002

Data Index: 184508 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0759. Min Act: -0.0003

Data Index: 201679 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0749. Min Act: -0.0003

Data Index: 112557 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0739. Min Act: -0.0004

Data Index: 516997 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0728. Min Act: -0.0002

Data Index: 544168 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0650. Min Act: -0.0003

Data Index: 659056 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1139701 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0712. Min Act: -0.0003

Data Index: 860704 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0699. Min Act: -0.0002

Data Index: 781530 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0705. Min Act: -0.0002

Data Index: 288813 (C4 (Web Text))

Max Activating Token Index: 484