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

Dataset: The Pile

Neuron 1971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1235. Min Range: -1.1235

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1256297 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8971. Min Act: -0.0000

Data Index: 880091 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8020. Min Act: -0.0000

Data Index: 388968 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8925. Min Act: -0.0000

Data Index: 559472 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1690969 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7879. Min Act: -0.0000

Data Index: 722630 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1881314 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1940804 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1443467 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8413. Min Act: -0.0000

Data Index: 768946 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7800. Min Act: -0.0000

Data Index: 987131 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7810. Min Act: -0.0000

Data Index: 902980 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1067350 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1592266 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7885. Min Act: -0.0000

Data Index: 989681 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8311. Min Act: -0.0000

Data Index: 467357 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7740. Min Act: -0.0000

Data Index: 154222 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1045379 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7527. Min Act: -0.0000

Data Index: 913287 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 1.1235. Min Range: -1.1235

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1773322 (The Pile)

Max Activating Token Index: 984