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

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

Neuron 1323 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: 0.7203. Min Range: -0.7203

Max Act: 0.7203. Min Act: -0.0001

Data Index: 1230922 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6424. Min Act: -0.0000

Data Index: 470435 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1120989 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6689. Min Act: -0.0001

Data Index: 1208119 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6510. Min Act: -0.0000

Data Index: 179033 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6879. Min Act: -0.0001

Data Index: 194461 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1017194 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6145. Min Act: -0.0001

Data Index: 1243102 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6404. Min Act: -0.0000

Data Index: 366395 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6177. Min Act: -0.0001

Data Index: 1084683 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6852. Min Act: -0.0000

Data Index: 891866 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1036964 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6123. Min Act: -0.0000

Data Index: 533382 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6082. Min Act: -0.0000

Data Index: 584451 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6195. Min Act: -0.0001

Data Index: 158059 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.6193. Min Act: -0.0000

Data Index: 443362 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5759. Min Act: -0.0001

Data Index: 794720 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5813. Min Act: -0.0001

Data Index: 544850 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5808. Min Act: -0.0001

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.7203. Min Range: -0.7203

Max Act: 0.5373. Min Act: -0.0001

Data Index: 1097901 (C4 (Web Text))

Max Activating Token Index: 556