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

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

Neuron 2180 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3471. Min Range: -6.3471

Max Act: 6.3471. Min Act: -0.0000

Data Index: 796472 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 6.3471. Min Range: -6.3471

Max Act: 4.6791. Min Act: -0.0000

Data Index: 350586 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 6.3471. Min Range: -6.3471

Max Act: 5.3116. Min Act: -0.0000

Data Index: 977181 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 6.3471. Min Range: -6.3471

Max Act: 5.2791. Min Act: -0.0000

Data Index: 940926 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 6.3471. Min Range: -6.3471

Max Act: 4.8626. Min Act: -0.0000

Data Index: 462921 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 6.3471. Min Range: -6.3471

Max Act: 4.6110. Min Act: -0.0000

Data Index: 837954 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 6.3471. Min Range: -6.3471

Max Act: 4.1159. Min Act: -0.0000

Data Index: 1346698 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.5847. Min Act: -0.0000

Data Index: 1013054 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.3814. Min Act: -0.0000

Data Index: 374176 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.8139. Min Act: -0.0000

Data Index: 696286 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.7892. Min Act: -0.0000

Data Index: 120096 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.3194. Min Act: -0.0000

Data Index: 1238726 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.3321. Min Act: -0.0000

Data Index: 724548 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.2922. Min Act: -0.0000

Data Index: 724474 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.2500. Min Act: -0.0000

Data Index: 1113537 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 6.3471. Min Range: -6.3471

Max Act: 2.8406. Min Act: -0.0000

Data Index: 1370744 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 6.3471. Min Range: -6.3471

Max Act: 3.5234. Min Act: -0.0000

Data Index: 585876 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 6.3471. Min Range: -6.3471

Max Act: 2.8943. Min Act: -0.0000

Data Index: 1090336 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 6.3471. Min Range: -6.3471

Max Act: 2.9892. Min Act: -0.0000

Data Index: 1430319 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 6.3471. Min Range: -6.3471

Max Act: 2.6398. Min Act: -0.0000

Data Index: 955216 (C4 (Web Text))

Max Activating Token Index: 770