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

Dataset: The Pile

Neuron 938 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.6656. Min Act: -0.0000

Data Index: 649610 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1157857 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4973. Min Act: -0.0000

Data Index: 102869 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5502. Min Act: -0.0000

Data Index: 884564 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1327097 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4774. Min Act: -0.0000

Data Index: 458688 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1702881 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4145. Min Act: -0.0000

Data Index: 12092 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4435. Min Act: -0.0000

Data Index: 779118 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1325644 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4041. Min Act: -0.0000

Data Index: 290352 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1182181 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1165624 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3860. Min Act: -0.0000

Data Index: 341415 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1803884 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1793261 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1609299 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1895915 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1809214 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1449853 (The Pile)

Max Activating Token Index: 164