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

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

Neuron 4775 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1036716 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.3161. Min Act: -0.0000

Data Index: 599583 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2514. Min Act: -0.0000

Data Index: 4858 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2598. Min Act: -0.0000

Data Index: 972171 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2495. Min Act: -0.0000

Data Index: 139695 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2658. Min Act: -0.0000

Data Index: 700210 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2508. Min Act: -0.0000

Data Index: 944736 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2517. Min Act: -0.0000

Data Index: 923233 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2551. Min Act: -0.0000

Data Index: 220011 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2426. Min Act: -0.0000

Data Index: 236080 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2417. Min Act: -0.0000

Data Index: 510501 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2278. Min Act: -0.0000

Data Index: 769967 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2229. Min Act: -0.0000

Data Index: 118121 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2229. Min Act: -0.0000

Data Index: 473006 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2034. Min Act: -0.0000

Data Index: 71043 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2172. Min Act: -0.0000

Data Index: 207742 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2118. Min Act: -0.0000

Data Index: 961549 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2030. Min Act: -0.0000

Data Index: 820650 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.1946. Min Act: -0.0000

Data Index: 126955 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2087. Min Act: -0.0000

Data Index: 848668 (C4 (Web Text))

Max Activating Token Index: 217