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

Dataset: The Pile

Neuron 21 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1682425 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.3902. Min Act: -0.0000

Data Index: 246949 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1081601 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.4752. Min Act: -0.0000

Data Index: 542449 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1822965 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1525741 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1383073 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.2977. Min Act: -0.0000

Data Index: 496209 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1797612 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1115908 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1973. Min Act: 0.0000

Data Index: 1080555 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.2135. Min Act: -0.0000

Data Index: 183256 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1663. Min Act: -0.0000

Data Index: 399199 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1306724 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1612. Min Act: -0.0000

Data Index: 238543 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1308. Min Act: -0.0000

Data Index: 117330 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1314. Min Act: -0.0000

Data Index: 34649 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1103607 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.0663. Min Act: -0.0000

Data Index: 26616 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 1.4922. Min Range: -1.4922

Max Act: 1.0491. Min Act: -0.0000

Data Index: 482393 (The Pile)

Max Activating Token Index: 935