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

Dataset: The Pile

Neuron 687 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: 1.4285. Min Range: -1.4285

Max Act: 1.4285. Min Act: -0.0000

Data Index: 370927 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1912957 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1583184 (The Pile)

Max Activating Token Index: 843

Text #3

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1194857 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2539. Min Act: -0.0000

Data Index: 965073 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1073021 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.3488. Min Act: -0.0000

Data Index: 177105 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2414. Min Act: -0.0000

Data Index: 1520025 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1951603 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1298482 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2640. Min Act: -0.0000

Data Index: 1674737 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2142. Min Act: -0.0000

Data Index: 772892 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.2535. Min Act: -0.0000

Data Index: 177306 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1017326 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1640199 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1402077 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1549. Min Act: -0.0000

Data Index: 102269 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0752. Min Act: -0.0000

Data Index: 160344 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1938406 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1026. Min Act: -0.0000

Data Index: 929519 (The Pile)

Max Activating Token Index: 29