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

Dataset: The Pile

Neuron 639 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.9916. Min Act: -0.0001

Data Index: 1140677 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.8734. Min Act: -0.0000

Data Index: 344703 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7535. Min Act: -0.0000

Data Index: 562916 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1619159 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1270823 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7382. Min Act: -0.0000

Data Index: 420473 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1550542 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6197. Min Act: -0.0001

Data Index: 1257444 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7150. Min Act: -0.0000

Data Index: 977578 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7036. Min Act: -0.0000

Data Index: 773753 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7001. Min Act: -0.0000

Data Index: 105392 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6254. Min Act: -0.0001

Data Index: 982350 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1165914 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6972. Min Act: -0.0000

Data Index: 962174 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6813. Min Act: -0.0000

Data Index: 788588 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6753. Min Act: -0.0000

Data Index: 251611 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1098398 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1106082 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.7222. Min Act: -0.0000

Data Index: 336417 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 0.9916. Min Range: -0.9916

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1323342 (The Pile)

Max Activating Token Index: 208