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

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

Neuron 4995 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: 0.4438. Min Range: -0.4438

Max Act: 0.4438. Min Act: -0.0000

Data Index: 165729 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3174. Min Act: -0.0000

Data Index: 685451 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2950. Min Act: -0.0000

Data Index: 102234 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2576. Min Act: -0.0000

Data Index: 751181 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2573. Min Act: -0.0000

Data Index: 172180 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1230123 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2289. Min Act: -0.0000

Data Index: 244384 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1932. Min Act: -0.0000

Data Index: 241900 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1997. Min Act: -0.0000

Data Index: 246099 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2052. Min Act: -0.0000

Data Index: 123009 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2105. Min Act: -0.0000

Data Index: 471194 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1645261 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1992. Min Act: -0.0000

Data Index: 869229 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1997. Min Act: -0.0000

Data Index: 239297 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1843. Min Act: -0.0000

Data Index: 680320 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1804. Min Act: -0.0000

Data Index: 613833 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1884. Min Act: -0.0000

Data Index: 902476 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1028831 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1752. Min Act: -0.0000

Data Index: 773974 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.1833. Min Act: -0.0000

Data Index: 708654 (C4 (Web Text))

Max Activating Token Index: 227