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

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

Neuron 1317 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.6612. Min Act: -0.0000

Data Index: 592933 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.7042. Min Act: -0.0000

Data Index: 460722 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.4258. Min Act: -0.0000

Data Index: 478106 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.4436. Min Act: -0.0000

Data Index: 738988 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.3903. Min Act: -0.0000

Data Index: 885957 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.4338. Min Act: -0.0000

Data Index: 879392 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.3307. Min Act: -0.0000

Data Index: 354871 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.3906. Min Act: -0.0000

Data Index: 876774 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2797. Min Act: -0.0000

Data Index: 302669 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2791. Min Act: -0.0000

Data Index: 1010484 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2676. Min Act: -0.0000

Data Index: 738830 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2635. Min Act: -0.0000

Data Index: 590148 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1148773 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2862. Min Act: -0.0000

Data Index: 76752 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2085. Min Act: -0.0000

Data Index: 695719 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1252948 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1139716 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1017777 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.1352. Min Act: -0.0000

Data Index: 996168 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.7042. Min Range: -1.7042

Max Act: 1.0176. Min Act: -0.0000

Data Index: 427962 (C4 (Web Text))

Max Activating Token Index: 476