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

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

Neuron 1012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0479. Min Range: -1.0479

Max Act: 1.0231. Min Act: -0.0001

Data Index: 1580527 (Python Code)

Max Activating Token Index: 228

Text #1

Max Range: 1.0479. Min Range: -1.0479

Max Act: 1.0428. Min Act: -0.0001

Data Index: 147248 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.0479. Min Range: -1.0479

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1351513 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.0479. Min Range: -1.0479

Max Act: 1.0435. Min Act: -0.0001

Data Index: 145057 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9947. Min Act: -0.0001

Data Index: 1574711 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9795. Min Act: -0.0001

Data Index: 1599425 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9802. Min Act: -0.0001

Data Index: 533147 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9703. Min Act: -0.0001

Data Index: 1640909 (Python Code)

Max Activating Token Index: 506

Text #8

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9723. Min Act: -0.0001

Data Index: 317195 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1501224 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9473. Min Act: -0.0001

Data Index: 255196 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1426490 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1595192 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9386. Min Act: -0.0001

Data Index: 1460178 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9867. Min Act: -0.0001

Data Index: 1611318 (Python Code)

Max Activating Token Index: 773

Text #15

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.8871. Min Act: -0.0001

Data Index: 1546584 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.9781. Min Act: -0.0001

Data Index: 285174 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.8393. Min Act: -0.0001

Data Index: 1559279 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.8887. Min Act: -0.0001

Data Index: 1542823 (Python Code)

Max Activating Token Index: 620

Text #19

Max Range: 1.0479. Min Range: -1.0479

Max Act: 0.8417. Min Act: -0.0001

Data Index: 1566616 (Python Code)

Max Activating Token Index: 666