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

Dataset: The Pile

Neuron 520 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: 3.9407. Min Range: -3.9407

Max Act: 3.5654. Min Act: -0.0000

Data Index: 545651 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.6920. Min Act: -0.0000

Data Index: 1213240 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.7154. Min Act: -0.0000

Data Index: 354644 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.9407. Min Act: -0.0000

Data Index: 477610 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.7474. Min Act: -0.0000

Data Index: 1708693 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.7301. Min Act: -0.0000

Data Index: 887972 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.1604. Min Act: -0.0000

Data Index: 305551 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.5895. Min Act: -0.0000

Data Index: 1099127 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.2742. Min Act: -0.0000

Data Index: 1535206 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.4382. Min Act: -0.0000

Data Index: 1911947 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.5335. Min Act: -0.0000

Data Index: 1382664 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.6934. Min Act: -0.0000

Data Index: 1757816 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.3259. Min Act: -0.0000

Data Index: 1919910 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.3003. Min Act: -0.0000

Data Index: 1048162 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.3139. Min Act: -0.0000

Data Index: 1846157 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 3.9407. Min Range: -3.9407

Max Act: 2.9093. Min Act: -0.0000

Data Index: 1948572 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.1912. Min Act: -0.0000

Data Index: 510503 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.4193. Min Act: -0.0000

Data Index: 1914082 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.4325. Min Act: -0.0000

Data Index: 332419 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 3.9407. Min Range: -3.9407

Max Act: 3.4225. Min Act: -0.0000

Data Index: 503899 (The Pile)

Max Activating Token Index: 845