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

Dataset: The Pile

Neuron 225 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: 1.0382. Min Range: -1.0382

Max Act: 1.0382. Min Act: -0.0000

Data Index: 364972 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1181952 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9640. Min Act: -0.0000

Data Index: 870525 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1477462 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9015. Min Act: -0.0000

Data Index: 233785 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8647. Min Act: -0.0000

Data Index: 251659 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1750828 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1812193 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.9064. Min Act: -0.0000

Data Index: 265809 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8681. Min Act: -0.0000

Data Index: 854738 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1752409 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8513. Min Act: -0.0000

Data Index: 836002 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1062455 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1657653 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8145. Min Act: -0.0000

Data Index: 733126 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1265295 (The Pile)

Max Activating Token Index: 979

Text #16

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7840. Min Act: -0.0000

Data Index: 375660 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.8542. Min Act: -0.0000

Data Index: 1421349 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7961. Min Act: -0.0000

Data Index: 565274 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 1.0382. Min Range: -1.0382

Max Act: 0.7538. Min Act: -0.0000

Data Index: 29232 (The Pile)

Max Activating Token Index: 472