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

Dataset: The Pile

Neuron 3142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2559. Min Range: -1.2559

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1884134 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 1.2559. Min Range: -1.2559

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1263829 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.2559. Min Range: -1.2559

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1589481 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.2559. Min Range: -1.2559

Max Act: 1.0037. Min Act: -0.0000

Data Index: 439198 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9531. Min Act: -0.0000

Data Index: 110252 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1827329 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9513. Min Act: -0.0000

Data Index: 167657 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.9495. Min Act: -0.0000

Data Index: 795471 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1238768 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1702815 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1461415 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8503. Min Act: -0.0000

Data Index: 533867 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8621. Min Act: -0.0000

Data Index: 92154 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.7997. Min Act: -0.0000

Data Index: 21957 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1993529 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1998159 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.7435. Min Act: -0.0000

Data Index: 63042 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1464929 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1149811 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 1.2559. Min Range: -1.2559

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1805366 (The Pile)

Max Activating Token Index: 644