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

Dataset: The Pile

Neuron 2240 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1990837 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5459. Min Act: -0.0000

Data Index: 542752 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4344. Min Act: -0.0000

Data Index: 869758 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1622632 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1298834 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1412718 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1100073 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1127851 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3673. Min Act: -0.0000

Data Index: 783394 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1418817 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3704. Min Act: -0.0000

Data Index: 946329 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3541. Min Act: -0.0000

Data Index: 476412 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3751. Min Act: -0.0000

Data Index: 740616 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1791193 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3931. Min Act: -0.0001

Data Index: 331301 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1357022 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3764. Min Act: -0.0000

Data Index: 987869 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1208374 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1625034 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1780843 (The Pile)

Max Activating Token Index: 957