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

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

Neuron 4972 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1316420 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.3969. Min Act: -0.0000

Data Index: 17115 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.3672. Min Act: -0.0000

Data Index: 319600 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.3621. Min Act: -0.0000

Data Index: 458291 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1276982 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.3514. Min Act: -0.0000

Data Index: 563607 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2534. Min Act: -0.0000

Data Index: 242588 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1427906 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.3100. Min Act: -0.0000

Data Index: 896035 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2852. Min Act: -0.0000

Data Index: 862252 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2742. Min Act: -0.0000

Data Index: 645717 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1180292 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2565. Min Act: -0.0000

Data Index: 784517 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.2815. Min Act: -0.0000

Data Index: 226335 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1912. Min Act: -0.0000

Data Index: 466786 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1875. Min Act: -0.0000

Data Index: 702761 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1055. Min Act: -0.0000

Data Index: 335375 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1158153 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.5847. Min Range: -1.5847

Max Act: 1.1620. Min Act: -0.0000

Data Index: 363534 (C4 (Web Text))

Max Activating Token Index: 1008