Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0001

Data Index: 375725 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6585. Min Act: -0.0001

Data Index: 96391 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6329. Min Act: -0.0001

Data Index: 722726 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6069. Min Act: -0.0001

Data Index: 1139680 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6282. Min Act: -0.0001

Data Index: 703257 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5414. Min Act: -0.0001

Data Index: 888395 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6151. Min Act: -0.0001

Data Index: 961210 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5798. Min Act: -0.0001

Data Index: 817887 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5756. Min Act: -0.0001

Data Index: 1211514 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5522. Min Act: -0.0001

Data Index: 168189 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5239. Min Act: -0.0001

Data Index: 350112 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5411. Min Act: -0.0001

Data Index: 152355 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5573. Min Act: -0.0001

Data Index: 162425 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1124105 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5514. Min Act: -0.0001

Data Index: 154797 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5361. Min Act: -0.0001

Data Index: 362830 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4898. Min Act: -0.0001

Data Index: 1342190 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5425. Min Act: -0.0001

Data Index: 514684 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5429. Min Act: -0.0001

Data Index: 717442 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1173128 (C4 (Web Text))

Max Activating Token Index: 977