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

Dataset: The Pile

Neuron 157 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: 0.3846. Min Range: -0.3846

Max Act: 0.3673. Min Act: 0.0000

Data Index: 30745 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1947187 (The Pile)

Max Activating Token Index: 649

Text #2

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3298. Min Act: -0.0000

Data Index: 525858 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1744184 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3280. Min Act: -0.0000

Data Index: 391925 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3288. Min Act: -0.0000

Data Index: 400240 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1511756 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1434779 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3021. Min Act: -0.0000

Data Index: 959691 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2917. Min Act: 0.0000

Data Index: 1431745 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2816. Min Act: -0.0000

Data Index: 831174 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1864159 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1903783 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1570380 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2812. Min Act: -0.0000

Data Index: 388684 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1399073 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2797. Min Act: -0.0000

Data Index: 493278 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2762. Min Act: -0.0000

Data Index: 195600 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1247775 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1553752 (The Pile)

Max Activating Token Index: 706