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

Dataset: The Pile

Neuron 3503 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1090279 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3233. Min Act: -0.0000

Data Index: 434964 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1914040 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2850. Min Act: -0.0000

Data Index: 483978 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1223020 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2571. Min Act: -0.0000

Data Index: 901464 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1392567 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2135. Min Act: -0.0000

Data Index: 910186 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2151. Min Act: -0.0000

Data Index: 424112 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2312. Min Act: -0.0000

Data Index: 663254 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1211723 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1799889 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2082. Min Act: -0.0000

Data Index: 709501 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2228. Min Act: -0.0000

Data Index: 79336 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2305. Min Act: -0.0000

Data Index: 711190 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1542186 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1003058 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.1963. Min Act: -0.0000

Data Index: 731408 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1572430 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2000. Min Act: -0.0000

Data Index: 443659 (The Pile)

Max Activating Token Index: 994