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

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

Neuron 392 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.8211. Min Act: -0.0001

Data Index: 19044 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.1979. Min Act: -0.0001

Data Index: 159407 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.1698. Min Act: -0.0001

Data Index: 147144 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.6508. Min Act: -0.0001

Data Index: 289769 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.6136. Min Act: -0.0001

Data Index: 206654 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.5076. Min Act: -0.0001

Data Index: 662301 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.4867. Min Act: -0.0001

Data Index: 1340721 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.3442. Min Act: -0.0001

Data Index: 1096270 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.3525. Min Act: -0.0001

Data Index: 621316 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.3078. Min Act: -0.0001

Data Index: 1059052 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.1348. Min Act: -0.0001

Data Index: 833856 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.1177. Min Act: -0.0001

Data Index: 16766 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.1626. Min Act: -0.0001

Data Index: 455744 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.1090. Min Act: -0.0001

Data Index: 538393 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 3.8211. Min Range: -3.8211

Max Act: 1.9543. Min Act: -0.0001

Data Index: 506236 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.1432. Min Act: -0.0001

Data Index: 90710 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.0111. Min Act: -0.0001

Data Index: 1309593 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 3.8211. Min Range: -3.8211

Max Act: 1.9795. Min Act: -0.0001

Data Index: 210267 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 3.8211. Min Range: -3.8211

Max Act: 2.1931. Min Act: -0.0001

Data Index: 625475 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 3.8211. Min Range: -3.8211

Max Act: 1.7714. Min Act: -0.0001

Data Index: 288198 (C4 (Web Text))

Max Activating Token Index: 729