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

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

Neuron 801 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.2641. Min Act: -0.0001

Data Index: 572291 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.3522. Min Act: -0.0001

Data Index: 708598 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1421. Min Act: -0.0001

Data Index: 487921 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0850. Min Act: -0.0001

Data Index: 520389 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0382. Min Act: -0.0001

Data Index: 514592 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0638. Min Act: -0.0001

Data Index: 1098875 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0858. Min Act: -0.0001

Data Index: 1254674 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0479. Min Act: -0.0001

Data Index: 565741 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0044. Min Act: -0.0001

Data Index: 97203 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0229. Min Act: -0.0001

Data Index: 101390 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9864. Min Act: -0.0001

Data Index: 1357994 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9925. Min Act: -0.0001

Data Index: 692001 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0064. Min Act: -0.0001

Data Index: 858096 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0061. Min Act: -0.0001

Data Index: 710594 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0244. Min Act: -0.0001

Data Index: 525072 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9889. Min Act: -0.0001

Data Index: 1104522 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9879. Min Act: -0.0001

Data Index: 62504 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1101540 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9638. Min Act: -0.0001

Data Index: 261015 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9965. Min Act: -0.0001

Data Index: 245049 (C4 (Web Text))

Max Activating Token Index: 632