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

Dataset: The Pile

Neuron 4042 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1699098 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.3267. Min Act: -0.0000

Data Index: 399625 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.3162. Min Act: -0.0000

Data Index: 372263 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1746. Min Act: -0.0000

Data Index: 68223 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1414655 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1679139 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1900679 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1232384 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0544. Min Act: -0.0000

Data Index: 934982 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0693. Min Act: -0.0000

Data Index: 552062 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1578. Min Act: -0.0000

Data Index: 824587 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.1173. Min Act: -0.0000

Data Index: 261159 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1191840 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0184. Min Act: -0.0000

Data Index: 258939 (The Pile)

Max Activating Token Index: 776

Text #14

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1092556 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1566190 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9696. Min Act: -0.0000

Data Index: 437298 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0041. Min Act: -0.0000

Data Index: 655441 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 1.3410. Min Range: -1.3410

Max Act: 1.0954. Min Act: -0.0000

Data Index: 147364 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 1.3410. Min Range: -1.3410

Max Act: 0.9938. Min Act: -0.0000

Data Index: 654118 (The Pile)

Max Activating Token Index: 949