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

Dataset: The Pile

Neuron 1955 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: 0.5140. Min Range: -0.5140

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1599685 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1004338 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1548853 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1159709 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.4165. Min Act: -0.0000

Data Index: 322029 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1471344 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3811. Min Act: -0.0000

Data Index: 340520 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1362351 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3851. Min Act: 0.0000

Data Index: 1738319 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3681. Min Act: 0.0000

Data Index: 479377 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3802. Min Act: 0.0000

Data Index: 571084 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1876884 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3662. Min Act: 0.0000

Data Index: 1716578 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3588. Min Act: 0.0000

Data Index: 1740785 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3750. Min Act: -0.0000

Data Index: 930531 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3648. Min Act: -0.0000

Data Index: 852904 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3460. Min Act: 0.0001

Data Index: 1549165 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1724790 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1243273 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.5140. Min Range: -0.5140

Max Act: 0.3424. Min Act: -0.0000

Data Index: 879682 (The Pile)

Max Activating Token Index: 63