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

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

Neuron 3667 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2483. Min Range: -1.2483

Max Act: 1.2483. Min Act: -0.0000

Data Index: 620063 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.2483. Min Range: -1.2483

Max Act: 1.0348. Min Act: -0.0000

Data Index: 123523 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.2483. Min Range: -1.2483

Max Act: 1.0259. Min Act: -0.0000

Data Index: 227668 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.9393. Min Act: -0.0000

Data Index: 935774 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.9483. Min Act: -0.0000

Data Index: 19006 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.9376. Min Act: -0.0000

Data Index: 8246 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1332482 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8865. Min Act: -0.0000

Data Index: 196986 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8789. Min Act: -0.0000

Data Index: 663600 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8201. Min Act: -0.0000

Data Index: 872613 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8631. Min Act: -0.0000

Data Index: 123152 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8237. Min Act: -0.0000

Data Index: 618703 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8094. Min Act: -0.0000

Data Index: 812099 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1337235 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8403. Min Act: -0.0000

Data Index: 8630 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1122868 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.7846. Min Act: -0.0000

Data Index: 746928 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.7759. Min Act: -0.0000

Data Index: 594538 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1153050 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 1.2483. Min Range: -1.2483

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1341374 (C4 (Web Text))

Max Activating Token Index: 233