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

Dataset: The Pile

Neuron 4023 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: 1.3979. Min Range: -1.3979

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1140407 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1611622 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1004271 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1625295 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1371. Min Act: -0.0000

Data Index: 113666 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0925. Min Act: -0.0000

Data Index: 862861 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1592500 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0673. Min Act: -0.0000

Data Index: 247203 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0128. Min Act: -0.0000

Data Index: 45041 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9853. Min Act: -0.0000

Data Index: 177164 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1033569 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1177995 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1344199 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9790. Min Act: -0.0000

Data Index: 505420 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1543088 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1418671 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9965. Min Act: -0.0000

Data Index: 682492 (The Pile)

Max Activating Token Index: 384

Text #17

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.8907. Min Act: -0.0000

Data Index: 605001 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9913. Min Act: -0.0000

Data Index: 212203 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.8735. Min Act: -0.0000

Data Index: 532273 (The Pile)

Max Activating Token Index: 795