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

Dataset: The Pile

Neuron 616 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: 0.7909. Min Range: -0.7909

Max Act: 0.7909. Min Act: -0.0000

Data Index: 543071 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5788. Min Act: -0.0000

Data Index: 179063 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1655646 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1570964 (The Pile)

Max Activating Token Index: 171

Text #4

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4457. Min Act: -0.0000

Data Index: 254464 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1680554 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1577785 (The Pile)

Max Activating Token Index: 801

Text #7

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4277. Min Act: -0.0000

Data Index: 122579 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4212. Min Act: -0.0000

Data Index: 827414 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1323733 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.4161. Min Act: -0.0000

Data Index: 898933 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3787. Min Act: -0.0000

Data Index: 693668 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3767. Min Act: -0.0000

Data Index: 121206 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3775. Min Act: -0.0000

Data Index: 353400 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3694. Min Act: -0.0000

Data Index: 952962 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1927680 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1312957 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3591. Min Act: -0.0000

Data Index: 304506 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1610891 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.3707. Min Act: -0.0000

Data Index: 122044 (The Pile)

Max Activating Token Index: 1019