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

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

Neuron 70 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: 2.0939. Min Range: -2.0939

Max Act: 1.9853. Min Act: -0.0000

Data Index: 795036 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 2.0939. Min Range: -2.0939

Max Act: 2.0939. Min Act: -0.0000

Data Index: 779192 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.9549. Min Act: -0.0000

Data Index: 524748 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.9051. Min Act: -0.0000

Data Index: 372786 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.8433. Min Act: -0.0000

Data Index: 249827 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.8183. Min Act: -0.0000

Data Index: 991500 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.7747. Min Act: -0.0000

Data Index: 643296 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1117923 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.7290. Min Act: -0.0000

Data Index: 524355 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.7631. Min Act: -0.0000

Data Index: 1200714 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.6513. Min Act: -0.0000

Data Index: 34325 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.6130. Min Act: -0.0000

Data Index: 356677 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.6026. Min Act: -0.0000

Data Index: 675375 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.5838. Min Act: -0.0000

Data Index: 188381 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.5829. Min Act: -0.0000

Data Index: 414556 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1309766 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.4861. Min Act: -0.0000

Data Index: 326087 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.5600. Min Act: -0.0000

Data Index: 1224884 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.5287. Min Act: -0.0000

Data Index: 24608 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 2.0939. Min Range: -2.0939

Max Act: 1.5056. Min Act: -0.0000

Data Index: 968329 (C4 (Web Text))

Max Activating Token Index: 985