Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2013 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.4223. Min Act: -0.0000

Data Index: 162300 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.3519. Min Act: -0.0000

Data Index: 277824 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2871. Min Act: -0.0000

Data Index: 1819337 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.1409. Min Act: -0.0000

Data Index: 866182 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.0180. Min Act: -0.0000

Data Index: 391780 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.1856. Min Act: -0.0000

Data Index: 604261 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.1257. Min Act: -0.0000

Data Index: 1970208 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9575. Min Act: -0.0000

Data Index: 657957 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2438. Min Act: -0.0000

Data Index: 215168 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.0437. Min Act: -0.0000

Data Index: 787086 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.0307. Min Act: -0.0000

Data Index: 1146216 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9832. Min Act: -0.0000

Data Index: 1254284 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9697. Min Act: -0.0000

Data Index: 1394034 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9461. Min Act: -0.0000

Data Index: 85643 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9497. Min Act: -0.0000

Data Index: 654853 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9397. Min Act: -0.0000

Data Index: 850025 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.9212. Min Act: -0.0000

Data Index: 1660906 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.8975. Min Act: -0.0000

Data Index: 1240797 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.8972. Min Act: -0.0000

Data Index: 162773 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 3.4223. Min Range: -3.4223

Max Act: 2.7224. Min Act: -0.0000

Data Index: 1977990 (The Pile)

Max Activating Token Index: 143