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

Dataset: The Pile

Neuron 3687 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: 1.4545. Min Range: -1.4545

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1519976 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.3923. Min Act: -0.0000

Data Index: 525479 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1091790 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1794494 (The Pile)

Max Activating Token Index: 381

Text #4

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.2706. Min Act: -0.0000

Data Index: 616210 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.3500. Min Act: -0.0000

Data Index: 151046 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1212381 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1284521 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1892354 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1642364 (The Pile)

Max Activating Token Index: 533

Text #10

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1127573 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.1321. Min Act: -0.0000

Data Index: 142591 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.1487. Min Act: -0.0000

Data Index: 723305 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1086720 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.0328. Min Act: -0.0000

Data Index: 33058 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 1.4545. Min Range: -1.4545

Max Act: 0.9120. Min Act: -0.0000

Data Index: 505771 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.0352. Min Act: -0.0000

Data Index: 133090 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 1.4545. Min Range: -1.4545

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1362240 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1963036 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 1.4545. Min Range: -1.4545

Max Act: 1.0857. Min Act: -0.0000

Data Index: 226535 (The Pile)

Max Activating Token Index: 258