Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4056 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6700. Min Act: -0.0000

Data Index: 25570 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6544. Min Act: -0.0000

Data Index: 907189 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1308344 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.6273. Min Act: -0.0000

Data Index: 313148 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5966. Min Act: -0.0000

Data Index: 264228 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5890. Min Act: -0.0000

Data Index: 542935 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5868. Min Act: -0.0001

Data Index: 967960 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1044139 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1312339 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1286581 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5849. Min Act: -0.0000

Data Index: 314593 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1298405 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1156287 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5630. Min Act: -0.0000

Data Index: 423828 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5356. Min Act: 0.0001

Data Index: 1203697 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1026784 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1093889 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5458. Min Act: -0.0000

Data Index: 495088 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1001559 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.6700. Min Range: -0.6700

Max Act: 0.5221. Min Act: -0.0001

Data Index: 145252 (C4 (Web Text))

Max Activating Token Index: 393