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

Dataset: The Pile

Neuron 1820 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: 0.5080. Min Range: -0.5080

Max Act: 0.5080. Min Act: -0.0000

Data Index: 282674 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3289. Min Act: -0.0000

Data Index: 367455 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1218139 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3586. Min Act: -0.0000

Data Index: 215626 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3637. Min Act: -0.0000

Data Index: 777926 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1412624 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3283. Min Act: -0.0000

Data Index: 1611087 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3507. Min Act: -0.0000

Data Index: 529519 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1326658 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1549409 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3229. Min Act: -0.0000

Data Index: 54375 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.2999. Min Act: -0.0000

Data Index: 512141 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3134. Min Act: -0.0000

Data Index: 171210 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1309368 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1549672 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1745091 (The Pile)

Max Activating Token Index: 618

Text #16

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1981960 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.2802. Min Act: -0.0000

Data Index: 563583 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3079. Min Act: -0.0000

Data Index: 987913 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1930231 (The Pile)

Max Activating Token Index: 849