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

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

Neuron 1003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.4958. Min Act: -0.0001

Data Index: 1032764 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.4410. Min Act: -0.0001

Data Index: 1349550 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.3969. Min Act: -0.0001

Data Index: 7634 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.3349. Min Act: -0.0001

Data Index: 729978 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.3587. Min Act: -0.0001

Data Index: 75163 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.3063. Min Act: -0.0001

Data Index: 636669 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.3161. Min Act: -0.0001

Data Index: 426191 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.2868. Min Act: -0.0001

Data Index: 1007037 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.2642. Min Act: -0.0001

Data Index: 1029832 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.2192. Min Act: -0.0001

Data Index: 611101 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1782. Min Act: -0.0001

Data Index: 489936 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1490. Min Act: -0.0001

Data Index: 190867 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1730. Min Act: -0.0001

Data Index: 821818 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1666. Min Act: -0.0001

Data Index: 1223982 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1216. Min Act: -0.0001

Data Index: 1195765 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1904. Min Act: -0.0001

Data Index: 1064700 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.3035. Min Act: -0.0001

Data Index: 992259 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1442. Min Act: -0.0001

Data Index: 1331122 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1209. Min Act: -0.0001

Data Index: 914176 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.4958. Min Range: -1.4958

Max Act: 1.1502. Min Act: -0.0001

Data Index: 1052587 (C4 (Web Text))

Max Activating Token Index: 282