Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.6808. Min Act: -0.0000

Data Index: 901386 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.6557. Min Act: -0.0000

Data Index: 170989 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1049344 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5550. Min Act: -0.0000

Data Index: 175950 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5504. Min Act: -0.0000

Data Index: 254634 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1972877 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1023685 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5175. Min Act: -0.0000

Data Index: 429390 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1937596 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5401. Min Act: -0.0001

Data Index: 347027 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.5017. Min Act: 0.0000

Data Index: 74880 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4856. Min Act: -0.0000

Data Index: 958072 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1382976 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1373010 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1957040 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1116097 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4867. Min Act: -0.0000

Data Index: 854430 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1895444 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4796. Min Act: -0.0000

Data Index: 657492 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 0.6808. Min Range: -0.6808

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1925342 (The Pile)

Max Activating Token Index: 524