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

Dataset: The Pile

Neuron 2697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5929. Min Range: -4.5929

Max Act: 4.5929. Min Act: -0.0000

Data Index: 1320395 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.8899. Min Act: -0.0000

Data Index: 571984 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.6423. Min Act: -0.0000

Data Index: 1218573 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.6306. Min Act: -0.0000

Data Index: 211893 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.6341. Min Act: -0.0000

Data Index: 1383441 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.5622. Min Act: -0.0000

Data Index: 1513111 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.5088. Min Act: -0.0000

Data Index: 1783925 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.6272. Min Act: -0.0000

Data Index: 1515990 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.5729. Min Act: -0.0000

Data Index: 1793004 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.1748. Min Act: -0.0000

Data Index: 715650 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.5507. Min Act: -0.0000

Data Index: 780970 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.2028. Min Act: -0.0000

Data Index: 1740645 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.0442. Min Act: -0.0000

Data Index: 1681753 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.7552. Min Act: -0.0000

Data Index: 1729117 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.0405. Min Act: -0.0000

Data Index: 1624118 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.3088. Min Act: -0.0000

Data Index: 87878 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.1275. Min Act: -0.0000

Data Index: 333773 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.3005. Min Act: -0.0000

Data Index: 1894022 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.2636. Min Act: -0.0000

Data Index: 579117 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 4.5929. Min Range: -4.5929

Max Act: 3.2422. Min Act: -0.0000

Data Index: 1783639 (The Pile)

Max Activating Token Index: 527