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

Dataset: The Pile

Neuron 3039 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4290. Min Act: -0.0000

Data Index: 720507 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1962370 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4583. Min Act: -0.0000

Data Index: 586873 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2847. Min Act: -0.0000

Data Index: 118357 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1622514 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1978268 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1240151 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2942. Min Act: -0.0000

Data Index: 594955 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1086395 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1197282 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1283601 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1010228 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1471746 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1848305 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1701450 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1242445 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1980. Min Act: -0.0000

Data Index: 1532901 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2419. Min Act: -0.0000

Data Index: 596382 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1648954 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1845. Min Act: -0.0000

Data Index: 54083 (The Pile)

Max Activating Token Index: 416