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

Dataset: The Pile

Neuron 2018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1022119 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.6303. Min Act: -0.0000

Data Index: 499773 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4680. Min Act: -0.0000

Data Index: 517138 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1685906 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4243. Min Act: -0.0000

Data Index: 334290 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4318. Min Act: -0.0000

Data Index: 49638 (The Pile)

Max Activating Token Index: 306

Text #6

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4426. Min Act: -0.0000

Data Index: 935841 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1160900 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1222852 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4326. Min Act: -0.0000

Data Index: 97489 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4152. Min Act: -0.0000

Data Index: 776677 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4244. Min Act: -0.0000

Data Index: 232854 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1329221 (The Pile)

Max Activating Token Index: 861

Text #13

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3932. Min Act: -0.0000

Data Index: 720283 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3954. Min Act: -0.0000

Data Index: 659721 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3885. Min Act: -0.0000

Data Index: 822275 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1249520 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3958. Min Act: -0.0000

Data Index: 851458 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3812. Min Act: -0.0000

Data Index: 906663 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3788. Min Act: -0.0000

Data Index: 680799 (The Pile)

Max Activating Token Index: 758