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

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

Neuron 3027 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: 1.1226. Min Range: -1.1226

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1286248 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.1226. Min Range: -1.1226

Max Act: 1.0767. Min Act: -0.0000

Data Index: 534166 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1050961 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.1226. Min Range: -1.1226

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1082435 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9609. Min Act: -0.0000

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9854. Min Act: -0.0000

Data Index: 706730 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8992. Min Act: -0.0000

Data Index: 787956 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1147380 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9089. Min Act: -0.0000

Data Index: 375558 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9070. Min Act: -0.0000

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8847. Min Act: -0.0000

Data Index: 509352 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8486. Min Act: -0.0000

Data Index: 806880 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8659. Min Act: -0.0000

Data Index: 585694 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.9405. Min Act: -0.0000

Data Index: 530080 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8200. Min Act: -0.0000

Data Index: 334001 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1169283 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1316856 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8490. Min Act: -0.0000

Data Index: 764464 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.1226. Min Range: -1.1226

Max Act: 0.8682. Min Act: -0.0000

Data Index: 788065 (C4 (Web Text))

Max Activating Token Index: 944