Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 640 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.3514. Min Act: -0.0000

Data Index: 511964 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2468. Min Act: -0.0000

Data Index: 220940 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.3039. Min Act: 0.0000

Data Index: 1641936 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1558463 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.2322. Min Act: 0.0000

Data Index: 1520651 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 1.3514. Min Range: -1.3514

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1654371 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1583212 (Python Code)

Max Activating Token Index: 759

Text #7

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1171202 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9329. Min Act: -0.0000

Data Index: 660475 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1423439 (Python Code)

Max Activating Token Index: 948

Text #10

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1544626 (Python Code)

Max Activating Token Index: 125

Text #11

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1381156 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1418828 (Python Code)

Max Activating Token Index: 488

Text #13

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7989. Min Act: -0.0000

Data Index: 514078 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7603. Min Act: -0.0000

Data Index: 198159 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1629477 (Python Code)

Max Activating Token Index: 523

Text #16

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1546111 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1053550 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.7571. Min Act: 0.0000

Data Index: 1504157 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 1.3514. Min Range: -1.3514

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1569419 (Python Code)

Max Activating Token Index: 154