Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.7099. Min Act: -0.0000

Data Index: 266146 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5954. Min Act: -0.0000

Data Index: 112527 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5780. Min Act: -0.0000

Data Index: 613244 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5819. Min Act: -0.0000

Data Index: 194190 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1311559 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1599737 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1640796 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1887039 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1579540 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5396. Min Act: -0.0000

Data Index: 952198 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1721323 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1698440 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5132. Min Act: -0.0000

Data Index: 603208 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1295702 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1006548 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1223095 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1765447 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1654373 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1040808 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.7099. Min Range: -0.7099

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1993144 (The Pile)

Max Activating Token Index: 469