Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1152 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0651. Min Act: -0.0005

Data Index: 933490 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0421. Min Act: -0.0004

Data Index: 194132 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0396. Min Act: -0.0005

Data Index: 1293177 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0388. Min Act: -0.0005

Data Index: 309415 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0416. Min Act: -0.0005

Data Index: 707402 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0382. Min Act: -0.0005

Data Index: 991665 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0371. Min Act: -0.0005

Data Index: 798595 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0371. Min Act: -0.0005

Data Index: 1304624 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0359. Min Act: -0.0005

Data Index: 808037 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0342. Min Act: -0.0005

Data Index: 334428 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0361. Min Act: -0.0005

Data Index: 777492 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0344. Min Act: -0.0005

Data Index: 97906 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0358. Min Act: -0.0005

Data Index: 218228 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0342. Min Act: -0.0005

Data Index: 858945 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0361. Min Act: -0.0005

Data Index: 560073 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0358. Min Act: -0.0005

Data Index: 989645 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0329. Min Act: -0.0005

Data Index: 1105679 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0325. Min Act: -0.0005

Data Index: 1260870 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0327. Min Act: -0.0005

Data Index: 625214 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0333. Min Act: -0.0005

Data Index: 918410 (C4 (Web Text))

Max Activating Token Index: 1005