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

Dataset: The Pile

Neuron 2736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7949. Min Act: -0.0000

Data Index: 455539 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1905052 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1808282 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6339. Min Act: -0.0000

Data Index: 247807 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1442108 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5161. Min Act: -0.0000

Data Index: 929439 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4916. Min Act: -0.0000

Data Index: 274674 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4750. Min Act: -0.0000

Data Index: 466422 (The Pile)

Max Activating Token Index: 539

Text #8

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4812. Min Act: -0.0000

Data Index: 512800 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4454. Min Act: -0.0000

Data Index: 238322 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4639. Min Act: -0.0000

Data Index: 561957 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4250. Min Act: -0.0000

Data Index: 820335 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1090275 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4215. Min Act: -0.0000

Data Index: 816855 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1364772 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1805578 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1304221 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.3961. Min Act: -0.0000

Data Index: 437072 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.3961. Min Act: 0.0000

Data Index: 1585091 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1945411 (The Pile)

Max Activating Token Index: 175