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

Dataset: The Pile

Neuron 365 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3768. Min Act: -0.0000

Data Index: 143746 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.4155. Min Act: -0.0000

Data Index: 302564 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1536663 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1187123 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3449. Min Act: -0.0000

Data Index: 767621 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3382. Min Act: -0.0000

Data Index: 24455 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1938974 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3159. Min Act: -0.0000

Data Index: 602464 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1217981 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2901. Min Act: -0.0000

Data Index: 172767 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3316. Min Act: -0.0000

Data Index: 197534 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3190. Min Act: -0.0000

Data Index: 416734 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1337036 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1472441 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2932. Min Act: -0.0000

Data Index: 226300 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3020. Min Act: -0.0000

Data Index: 768119 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2817. Min Act: -0.0000

Data Index: 179606 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2891. Min Act: -0.0000

Data Index: 303135 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2498. Min Act: -0.0000

Data Index: 533279 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1463510 (The Pile)

Max Activating Token Index: 586