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

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

Neuron 4504 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.7342. Min Act: -0.0001

Data Index: 272104 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.4260. Min Act: -0.0001

Data Index: 198258 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.5503. Min Act: -0.0001

Data Index: 422199 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.3601. Min Act: -0.0001

Data Index: 317254 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.4483. Min Act: -0.0001

Data Index: 246016 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.2497. Min Act: -0.0001

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.2327. Min Act: -0.0001

Data Index: 907429 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.3276. Min Act: -0.0001

Data Index: 160466 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.1689. Min Act: -0.0001

Data Index: 647861 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.5311. Min Act: -0.0001

Data Index: 723303 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.3692. Min Act: -0.0001

Data Index: 837571 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.1132. Min Act: -0.0001

Data Index: 183702 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.1924. Min Act: -0.0001

Data Index: 648038 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.2004. Min Act: -0.0001

Data Index: 1149120 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.2644. Min Act: -0.0001

Data Index: 1218094 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.2644. Min Act: -0.0001

Data Index: 575376 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.1583. Min Act: -0.0000

Data Index: 405457 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.0610. Min Act: -0.0001

Data Index: 939576 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.1326. Min Act: -0.0001

Data Index: 62586 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.7342. Min Range: -1.7342

Max Act: 1.1802. Min Act: -0.0001

Data Index: 1158012 (C4 (Web Text))

Max Activating Token Index: 460