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

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

Neuron 2405 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.1514. Min Act: -0.0001

Data Index: 442144 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0424. Min Act: -0.0001

Data Index: 661669 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9129. Min Act: -0.0001

Data Index: 31866 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8668. Min Act: -0.0001

Data Index: 419364 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8660. Min Act: -0.0001

Data Index: 723949 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8489. Min Act: -0.0001

Data Index: 48007 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7732. Min Act: -0.0001

Data Index: 216556 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8718. Min Act: -0.0001

Data Index: 251798 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7860. Min Act: -0.0001

Data Index: 1624155 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8215. Min Act: -0.0001

Data Index: 319384 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7521. Min Act: -0.0001

Data Index: 844016 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7200. Min Act: -0.0001

Data Index: 185996 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6737. Min Act: -0.0001

Data Index: 759144 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7075. Min Act: -0.0001

Data Index: 596971 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1358996 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7513. Min Act: -0.0001

Data Index: 1063897 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1595619 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7044. Min Act: -0.0001

Data Index: 132484 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7163. Min Act: -0.0001

Data Index: 554770 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7005. Min Act: -0.0001

Data Index: 695190 (C4 (Web Text))

Max Activating Token Index: 603