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

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

Neuron 2820 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: 1.8262. Min Range: -1.8262

Max Act: 1.8262. Min Act: -0.0001

Data Index: 1190570 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.7198. Min Act: -0.0001

Data Index: 104189 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.5168. Min Act: -0.0001

Data Index: 231642 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.6269. Min Act: -0.0001

Data Index: 1312328 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.6088. Min Act: -0.0001

Data Index: 1163267 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.6523. Min Act: -0.0001

Data Index: 980034 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.5512. Min Act: -0.0001

Data Index: 1234716 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.3741. Min Act: -0.0001

Data Index: 110740 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.5253. Min Act: -0.0001

Data Index: 524700 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.3125. Min Act: -0.0000

Data Index: 208352 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.3721. Min Act: -0.0001

Data Index: 479880 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.3429. Min Act: -0.0001

Data Index: 630630 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.2935. Min Act: -0.0000

Data Index: 326852 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.3267. Min Act: -0.0001

Data Index: 1058891 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.2609. Min Act: -0.0001

Data Index: 968414 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.3256. Min Act: -0.0001

Data Index: 380448 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.2077. Min Act: -0.0001

Data Index: 1273744 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.1114. Min Act: -0.0001

Data Index: 1157320 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.2970. Min Act: -0.0000

Data Index: 870675 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.8262. Min Range: -1.8262

Max Act: 1.1465. Min Act: -0.0001

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 694