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

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

Neuron 4084 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: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0001

Data Index: 966301 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1430. Min Act: -0.0001

Data Index: 301128 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1453. Min Act: -0.0001

Data Index: 655174 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1488. Min Act: -0.0001

Data Index: 189755 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1286. Min Act: -0.0001

Data Index: 387162 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1258. Min Act: -0.0001

Data Index: 609055 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1328. Min Act: -0.0001

Data Index: 137072 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1070841 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1400. Min Act: -0.0001

Data Index: 646922 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1100. Min Act: -0.0001

Data Index: 821766 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1086. Min Act: -0.0001

Data Index: 785870 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1071. Min Act: -0.0001

Data Index: 225393 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1026. Min Act: -0.0001

Data Index: 594163 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1181. Min Act: -0.0001

Data Index: 990499 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1017. Min Act: -0.0001

Data Index: 389415 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1212886 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0935. Min Act: -0.0001

Data Index: 59874 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1000. Min Act: -0.0001

Data Index: 349888 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0952. Min Act: -0.0001

Data Index: 803579 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1055. Min Act: -0.0001

Data Index: 707591 (C4 (Web Text))

Max Activating Token Index: 635