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

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

Neuron 1765 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1095. Min Range: -3.1095

Max Act: 3.1095. Min Act: -0.0000

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.5228. Min Act: -0.0001

Data Index: 1015261 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.4039. Min Act: -0.0001

Data Index: 342640 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.5169. Min Act: -0.0001

Data Index: 205072 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.3166. Min Act: -0.0000

Data Index: 1052633 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.2660. Min Act: -0.0001

Data Index: 207202 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.2170. Min Act: -0.0001

Data Index: 1037343 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.2695. Min Act: -0.0000

Data Index: 1196128 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.0173. Min Act: -0.0001

Data Index: 596495 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.1213. Min Act: -0.0001

Data Index: 698369 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.0477. Min Act: -0.0001

Data Index: 1159085 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1045802 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.8619. Min Act: -0.0001

Data Index: 827918 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.0259. Min Act: -0.0001

Data Index: 117941 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.7625. Min Act: -0.0001

Data Index: 362806 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.8032. Min Act: -0.0001

Data Index: 804408 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.7524. Min Act: -0.0001

Data Index: 703696 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 3.1095. Min Range: -3.1095

Max Act: 2.0620. Min Act: -0.0001

Data Index: 241284 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.8309. Min Act: -0.0001

Data Index: 823167 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 3.1095. Min Range: -3.1095

Max Act: 1.8906. Min Act: -0.0001

Data Index: 1171116 (C4 (Web Text))

Max Activating Token Index: 261