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

Dataset: The Pile

Neuron 2874 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: 1.3646. Min Range: -1.3646

Max Act: 1.3646. Min Act: -0.0000

Data Index: 1234848 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3366. Min Act: -0.0000

Data Index: 1949701 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1422470 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1264552 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1817127 (The Pile)

Max Activating Token Index: 730

Text #5

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1096234 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2333. Min Act: -0.0000

Data Index: 1229117 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1747809 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2945. Min Act: -0.0000

Data Index: 234791 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1787267 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1223407 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1412. Min Act: -0.0000

Data Index: 1494720 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1364177 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1230351 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1926. Min Act: -0.0000

Data Index: 374058 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1857751 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1169. Min Act: -0.0000

Data Index: 86224 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1914508 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1335454 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1541. Min Act: -0.0000

Data Index: 539391 (The Pile)

Max Activating Token Index: 228