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

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

Neuron 1779 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.9768. Min Act: -0.0000

Data Index: 306584 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1056411 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3970. Min Act: -0.0000

Data Index: 779485 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2164. Min Act: -0.0000

Data Index: 899560 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3120. Min Act: -0.0000

Data Index: 592377 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1553. Min Act: -0.0000

Data Index: 1080025 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1334814 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1099231 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1017. Min Act: -0.0000

Data Index: 68225 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2329. Min Act: -0.0000

Data Index: 696527 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1497. Min Act: -0.0000

Data Index: 965873 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1174. Min Act: -0.0000

Data Index: 908814 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1819. Min Act: -0.0000

Data Index: 227746 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1269206 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0499. Min Act: -0.0000

Data Index: 279562 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1140932 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0495. Min Act: -0.0000

Data Index: 82786 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1018977 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0379. Min Act: -0.0000

Data Index: 684022 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.9768. Min Range: -1.9768

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1276615 (C4 (Web Text))

Max Activating Token Index: 761