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

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

Neuron 3100 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4456. Min Range: -2.4456

Max Act: 2.4456. Min Act: -0.0000

Data Index: 1159846 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.4456. Min Range: -2.4456

Max Act: 2.0279. Min Act: -0.0000

Data Index: 254184 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1023453 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.8203. Min Act: -0.0000

Data Index: 204472 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.8025. Min Act: -0.0000

Data Index: 402491 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.6651. Min Act: -0.0000

Data Index: 2444 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1035497 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.3275. Min Act: -0.0000

Data Index: 983894 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.4033. Min Act: -0.0000

Data Index: 352992 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.4046. Min Act: -0.0000

Data Index: 786181 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.4005. Min Act: -0.0000

Data Index: 424360 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1178697 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.3435. Min Act: -0.0000

Data Index: 126631 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1080289 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.4161. Min Act: -0.0000

Data Index: 209180 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1053131 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.3731. Min Act: -0.0000

Data Index: 506369 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1065732 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.2413. Min Act: -0.0000

Data Index: 416805 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 2.4456. Min Range: -2.4456

Max Act: 1.2531. Min Act: -0.0000

Data Index: 655666 (C4 (Web Text))

Max Activating Token Index: 725