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

Dataset: The Pile

Neuron 1188 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: 1.9347. Min Range: -1.9347

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1430197 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.6526. Min Act: -0.0000

Data Index: 810145 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.4128. Min Act: -0.0000

Data Index: 445497 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1966561 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1734843 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1617756 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1900125 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.2842. Min Act: -0.0000

Data Index: 830979 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1748483 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1465910 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.1615. Min Act: -0.0000

Data Index: 641615 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.9594. Min Act: -0.0000

Data Index: 865073 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.9967. Min Act: -0.0000

Data Index: 417981 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.9347. Min Range: -1.9347

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1710993 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.9947. Min Act: -0.0000

Data Index: 459139 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1876175 (The Pile)

Max Activating Token Index: 315

Text #16

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.9492. Min Act: -0.0000

Data Index: 242091 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1574543 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1866235 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 1.9347. Min Range: -1.9347

Max Act: 0.8827. Min Act: -0.0000

Data Index: 575601 (The Pile)

Max Activating Token Index: 456