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

Dataset: The Pile

Neuron 2044 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: 0.5203. Min Range: -0.5203

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1894752 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5203. Min Act: -0.0000

Data Index: 666986 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1423195 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1237313 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4826. Min Act: -0.0000

Data Index: 880375 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4521. Min Act: -0.0000

Data Index: 768322 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4223. Min Act: -0.0000

Data Index: 861246 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4336. Min Act: -0.0000

Data Index: 512584 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4066. Min Act: -0.0000

Data Index: 446605 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1914868 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4192. Min Act: -0.0000

Data Index: 164639 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1747087 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1603708 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1439712 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1312390 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1278645 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1699181 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1409413 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1694214 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1767063 (The Pile)

Max Activating Token Index: 44