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

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

Neuron 811 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.8772. Min Act: -0.0001

Data Index: 207916 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6109. Min Act: -0.0001

Data Index: 813680 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4111. Min Act: -0.0001

Data Index: 791795 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4070. Min Act: -0.0001

Data Index: 17767 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5510. Min Act: -0.0001

Data Index: 282629 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5219. Min Act: -0.0001

Data Index: 567471 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4770. Min Act: -0.0001

Data Index: 629970 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4475. Min Act: -0.0001

Data Index: 1146191 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4488. Min Act: -0.0001

Data Index: 509545 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4338. Min Act: -0.0001

Data Index: 1234542 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.2985. Min Act: -0.0001

Data Index: 334679 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4335. Min Act: -0.0001

Data Index: 978459 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.2781. Min Act: -0.0001

Data Index: 356633 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4266. Min Act: -0.0001

Data Index: 111429 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4188. Min Act: -0.0001

Data Index: 607967 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4117. Min Act: -0.0001

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.1043. Min Act: -0.0001

Data Index: 6132 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4339. Min Act: -0.0001

Data Index: 1214449 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4206. Min Act: -0.0001

Data Index: 296977 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.2464. Min Act: -0.0001

Data Index: 608207 (C4 (Web Text))

Max Activating Token Index: 894