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

Dataset: The Pile

Neuron 1137 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.3842. Min Act: -0.0000

Data Index: 902862 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1159. Min Act: -0.0000

Data Index: 183714 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0238. Min Act: -0.0000

Data Index: 262832 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0809. Min Act: -0.0000

Data Index: 195084 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1364774 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1484875 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0144. Min Act: -0.0000

Data Index: 414663 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1469503 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1433703 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9767. Min Act: -0.0000

Data Index: 121483 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8936. Min Act: -0.0000

Data Index: 731833 (The Pile)

Max Activating Token Index: 7

Text #11

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8363. Min Act: -0.0000

Data Index: 328698 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1123402 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1768273 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1106596 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8325. Min Act: -0.0000

Data Index: 308191 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1524488 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1673999 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1335072 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8277. Min Act: -0.0000

Data Index: 417583 (The Pile)

Max Activating Token Index: 875