Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2464. Min Range: -1.2464

Max Act: 1.2464. Min Act: -0.0001

Data Index: 324277 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.4896. Min Act: -0.0001

Data Index: 961741 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1146109 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.5146. Min Act: -0.0001

Data Index: 313972 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.3549. Min Act: -0.0001

Data Index: 319985 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1640. Min Act: -0.0001

Data Index: 65800 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.2651. Min Act: -0.0001

Data Index: 220057 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1835. Min Act: -0.0001

Data Index: 561181 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1442. Min Act: -0.0001

Data Index: 860069 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1517. Min Act: -0.0001

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1538. Min Act: -0.0001

Data Index: 156482 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1534. Min Act: -0.0001

Data Index: 669979 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1437. Min Act: -0.0001

Data Index: 238698 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1359. Min Act: -0.0001

Data Index: 637877 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1161473 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1347. Min Act: -0.0001

Data Index: 385004 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1313. Min Act: -0.0001

Data Index: 707901 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1067059 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.2464. Min Range: -1.2464

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1032445 (C4 (Web Text))

Max Activating Token Index: 791