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

Dataset: The Pile

Neuron 763 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: 1.6588. Min Range: -1.6588

Max Act: 1.5102. Min Act: -0.0000

Data Index: 983665 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.6588. Min Act: -0.0000

Data Index: 139620 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4006. Min Act: -0.0000

Data Index: 38075 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1209016 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3680. Min Act: -0.0000

Data Index: 957838 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3323. Min Act: -0.0000

Data Index: 770622 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1762519 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4445. Min Act: -0.0000

Data Index: 210099 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4498. Min Act: -0.0000

Data Index: 459200 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3451. Min Act: -0.0000

Data Index: 971552 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1040366 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1771634 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1214944 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1583538 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1616221 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3213. Min Act: -0.0000

Data Index: 702618 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2648. Min Act: -0.0000

Data Index: 332837 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1811121 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1364209 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1387129 (The Pile)

Max Activating Token Index: 82