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

Dataset: The Pile

Neuron 1216 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.5026. Min Act: -0.0000

Data Index: 74845 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.6905. Min Act: -0.0000

Data Index: 1025221 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.3934. Min Act: -0.0000

Data Index: 1079627 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.1904. Min Act: -0.0000

Data Index: 518654 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.3588. Min Act: -0.0000

Data Index: 336365 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.2832. Min Act: -0.0000

Data Index: 763211 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.4699. Min Act: -0.0000

Data Index: 421914 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.1205. Min Act: -0.0000

Data Index: 109853 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.4255. Min Act: -0.0000

Data Index: 1778350 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.0369. Min Act: -0.0000

Data Index: 1229462 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.2191. Min Act: -0.0000

Data Index: 1559447 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.0473. Min Act: -0.0000

Data Index: 1352192 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.3609. Min Act: -0.0000

Data Index: 1769316 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 5.6905. Min Range: -5.6905

Max Act: 4.9950. Min Act: -0.0000

Data Index: 893175 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 5.6905. Min Range: -5.6905

Max Act: 4.9469. Min Act: -0.0000

Data Index: 1546030 (The Pile)

Max Activating Token Index: 796

Text #15

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.2958. Min Act: -0.0000

Data Index: 893492 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.0975. Min Act: -0.0000

Data Index: 1657636 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 5.6905. Min Range: -5.6905

Max Act: 4.9022. Min Act: -0.0000

Data Index: 184947 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 5.6905. Min Range: -5.6905

Max Act: 4.9121. Min Act: -0.0000

Data Index: 110928 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 5.6905. Min Range: -5.6905

Max Act: 5.2410. Min Act: -0.0000

Data Index: 371069 (The Pile)

Max Activating Token Index: 105