Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6055 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.8259. Min Act: -0.0000

Data Index: 937555 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.5526. Min Act: -0.0000

Data Index: 386373 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.5275. Min Act: -0.0000

Data Index: 873565 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.1732. Min Act: -0.0000

Data Index: 853745 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4949. Min Act: -0.0000

Data Index: 747144 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.2779. Min Act: -0.0000

Data Index: 671390 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.0968. Min Act: -0.0000

Data Index: 540958 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.0613. Min Act: -0.0000

Data Index: 735399 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.1725. Min Act: -0.0000

Data Index: 489099 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.2888. Min Act: -0.0000

Data Index: 734786 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.9552. Min Act: -0.0000

Data Index: 1274338 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.9338. Min Act: -0.0000

Data Index: 1296227 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.0497. Min Act: -0.0000

Data Index: 640420 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.8819. Min Act: -0.0000

Data Index: 316944 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.9877. Min Act: -0.0000

Data Index: 561319 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.9474. Min Act: -0.0000

Data Index: 510860 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.8181. Min Act: -0.0000

Data Index: 1148004 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.3671. Min Act: -0.0000

Data Index: 557773 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.9118. Min Act: -0.0000

Data Index: 671696 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 3.8259. Min Range: -3.8259

Max Act: 2.6376. Min Act: -0.0000

Data Index: 1309583 (C4 (Web Text))

Max Activating Token Index: 648