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

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

Neuron 5118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3168. Min Range: -2.3168

Max Act: 2.3168. Min Act: -0.0000

Data Index: 1187831 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 2.3168. Min Range: -2.3168

Max Act: 2.2593. Min Act: -0.0000

Data Index: 332555 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 2.3168. Min Range: -2.3168

Max Act: 2.2050. Min Act: -0.0000

Data Index: 1064828 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 2.3168. Min Range: -2.3168

Max Act: 2.1898. Min Act: -0.0000

Data Index: 1092477 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 2.3168. Min Range: -2.3168

Max Act: 2.0624. Min Act: -0.0000

Data Index: 117260 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.8843. Min Act: -0.0000

Data Index: 935274 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.8794. Min Act: -0.0000

Data Index: 797008 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.7644. Min Act: -0.0000

Data Index: 917997 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.8252. Min Act: -0.0000

Data Index: 912664 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.7336. Min Act: -0.0000

Data Index: 1303709 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.7285. Min Act: -0.0000

Data Index: 44881 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.5801. Min Act: -0.0000

Data Index: 323387 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.6438. Min Act: -0.0000

Data Index: 902491 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1128941 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.6075. Min Act: -0.0000

Data Index: 1229433 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.5991. Min Act: -0.0000

Data Index: 97531 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1194408 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1178516 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.6035. Min Act: -0.0000

Data Index: 195983 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 2.3168. Min Range: -2.3168

Max Act: 1.5134. Min Act: -0.0000

Data Index: 103172 (C4 (Web Text))

Max Activating Token Index: 880