Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1365 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4711. Min Act: -0.0005

Data Index: 395790 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4716. Min Act: -0.0005

Data Index: 901851 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4556. Min Act: -0.0005

Data Index: 1176447 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4630. Min Act: -0.0005

Data Index: 1088384 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4713. Min Act: -0.0005

Data Index: 855031 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4386. Min Act: -0.0005

Data Index: 1215509 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4335. Min Act: -0.0005

Data Index: 1335420 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4315. Min Act: -0.0005

Data Index: 1232893 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4334. Min Act: -0.0005

Data Index: 915273 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4437. Min Act: -0.0005

Data Index: 1163394 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4315. Min Act: -0.0005

Data Index: 1337886 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4169. Min Act: -0.0005

Data Index: 1079472 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4336. Min Act: -0.0005

Data Index: 722276 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4175. Min Act: -0.0005

Data Index: 1212499 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4012. Min Act: -0.0005

Data Index: 351345 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4068. Min Act: -0.0005

Data Index: 146927 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4072. Min Act: -0.0005

Data Index: 1140644 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4070. Min Act: -0.0005

Data Index: 1327345 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.4206. Min Act: -0.0005

Data Index: 1007151 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.4716. Min Range: -0.4716

Max Act: 0.3858. Min Act: -0.0005

Data Index: 915807 (C4 (Web Text))

Max Activating Token Index: 353