Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1009 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1091. Min Range: -3.1091

Max Act: 3.1091. Min Act: -0.0000

Data Index: 1097689 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.6860. Min Act: -0.0000

Data Index: 1231053 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.5373. Min Act: -0.0000

Data Index: 1020957 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.7022. Min Act: -0.0000

Data Index: 336316 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.3999. Min Act: -0.0000

Data Index: 1082096 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.3441. Min Act: -0.0000

Data Index: 1223594 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.4620. Min Act: -0.0000

Data Index: 948725 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.5217. Min Act: -0.0000

Data Index: 254922 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2047. Min Act: -0.0000

Data Index: 214934 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.3880. Min Act: -0.0000

Data Index: 458749 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2976. Min Act: -0.0000

Data Index: 323485 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2378. Min Act: -0.0000

Data Index: 303447 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2234. Min Act: -0.0000

Data Index: 981696 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.0915. Min Act: -0.0000

Data Index: 546283 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2178. Min Act: -0.0000

Data Index: 1176516 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.3244. Min Act: -0.0000

Data Index: 503798 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2201. Min Act: -0.0000

Data Index: 979057 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 3.1091. Min Range: -3.1091

Max Act: 2.2262. Min Act: -0.0000

Data Index: 561919 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.1091. Min Range: -3.1091

Max Act: 1.8752. Min Act: -0.0000

Data Index: 522916 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 3.1091. Min Range: -3.1091

Max Act: 1.9918. Min Act: -0.0000

Data Index: 845996 (C4 (Web Text))

Max Activating Token Index: 538