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

Dataset: The Pile

Neuron 4757 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: 0.4938. Min Range: -0.4938

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1110763 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4799. Min Act: -0.0000

Data Index: 29242 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1795914 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4531. Min Act: -0.0000

Data Index: 926916 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1769681 (The Pile)

Max Activating Token Index: 83

Text #5

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1909164 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1564 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4345. Min Act: -0.0000

Data Index: 431158 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1422124 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4029. Min Act: -0.0000

Data Index: 302077 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1567900 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1151759 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3895. Min Act: -0.0000

Data Index: 988459 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1924248 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1816295 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3804. Min Act: -0.0000

Data Index: 619922 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3749. Min Act: -0.0000

Data Index: 805938 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1103963 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1064413 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3278. Min Act: -0.0000

Data Index: 65883 (The Pile)

Max Activating Token Index: 214