Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2923 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.8841. Min Act: -0.0000

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.7110. Min Act: -0.0000

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1445434 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1070526 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1462658 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1284102 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.2825. Min Act: -0.0000

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1186144 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.2940. Min Act: -0.0000

Data Index: 141466 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.2144. Min Act: -0.0000

Data Index: 3028 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1502143 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.2866. Min Act: -0.0000

Data Index: 378072 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1477593 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1414482 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1543891 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.1438. Min Act: -0.0000

Data Index: 1435925 (Python Code)

Max Activating Token Index: 479

Text #17

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.0624. Min Act: -0.0000

Data Index: 813953 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1049203 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.8841. Min Range: -1.8841

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 560