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

Dataset: The Pile

Neuron 2257 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: 0.6033. Min Range: -0.6033

Max Act: 0.6033. Min Act: -0.0000

Data Index: 640078 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1095507 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1071537 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4858. Min Act: -0.0000

Data Index: 147117 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4981. Min Act: -0.0000

Data Index: 442893 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4872. Min Act: -0.0000

Data Index: 319517 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4922. Min Act: -0.0000

Data Index: 771487 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1158110 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1841422 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1461697 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1302110 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1222996 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4286. Min Act: -0.0000

Data Index: 844166 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4039. Min Act: -0.0000

Data Index: 196301 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4402. Min Act: -0.0000

Data Index: 987508 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1114944 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1537742 (The Pile)

Max Activating Token Index: 180

Text #17

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1344951 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4267. Min Act: -0.0000

Data Index: 613584 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4007. Min Act: -0.0000

Data Index: 671516 (The Pile)

Max Activating Token Index: 794