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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2385 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.1852. Min Act: -0.0000

Data Index: 651187 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0094. Min Act: -0.0000

Data Index: 365832 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0916. Min Act: -0.0000

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1166516 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0637. Min Act: -0.0000

Data Index: 410004 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.1123. Min Act: -0.0000

Data Index: 345274 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0454. Min Act: -0.0000

Data Index: 122140 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0142. Min Act: -0.0000

Data Index: 706608 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0140. Min Act: -0.0001

Data Index: 748414 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9599. Min Act: -0.0001

Data Index: 755395 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1006305 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.1852. Min Range: -1.1852

Max Act: 1.0020. Min Act: -0.0001

Data Index: 986094 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1258824 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9672. Min Act: -0.0000

Data Index: 800894 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9042. Min Act: -0.0000

Data Index: 293259 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1334859 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9670. Min Act: -0.0001

Data Index: 912093 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1254520 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.9469. Min Act: -0.0000

Data Index: 878322 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.1852. Min Range: -1.1852

Max Act: 0.8904. Min Act: -0.0001

Data Index: 863802 (C4 (Web Text))

Max Activating Token Index: 803