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

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

Neuron 3543 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5559. Min Range: -1.5559

Max Act: 1.5559. Min Act: -0.0001

Data Index: 176634 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.5559. Min Range: -1.5559

Max Act: 1.2665. Min Act: -0.0001

Data Index: 1619361 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 1.5559. Min Range: -1.5559

Max Act: 1.3549. Min Act: -0.0001

Data Index: 1571949 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 1.5559. Min Range: -1.5559

Max Act: 1.3502. Min Act: -0.0001

Data Index: 1393102 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 1.5559. Min Range: -1.5559

Max Act: 1.1067. Min Act: -0.0001

Data Index: 1472839 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9948. Min Act: -0.0001

Data Index: 1638457 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9675. Min Act: -0.0001

Data Index: 485420 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9344. Min Act: -0.0001

Data Index: 1439213 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9875. Min Act: -0.0001

Data Index: 1429025 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9233. Min Act: -0.0001

Data Index: 1418905 (Python Code)

Max Activating Token Index: 310

Text #10

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9426. Min Act: -0.0001

Data Index: 1298092 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9047. Min Act: -0.0001

Data Index: 1425030 (Python Code)

Max Activating Token Index: 264

Text #12

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9604. Min Act: -0.0001

Data Index: 1446784 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9233. Min Act: -0.0001

Data Index: 954579 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1480545 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1396861 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.8551. Min Act: -0.0001

Data Index: 1555263 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1535516 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.8166. Min Act: -0.0001

Data Index: 1419464 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 1.5559. Min Range: -1.5559

Max Act: 0.8513. Min Act: -0.0001

Data Index: 1395623 (Python Code)

Max Activating Token Index: 296