Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 341 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7882. Min Range: -4.7882

Max Act: 4.6311. Min Act: -0.0000

Data Index: 808005 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 4.7882. Min Range: -4.7882

Max Act: 4.7882. Min Act: -0.0000

Data Index: 743178 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 4.7882. Min Range: -4.7882

Max Act: 4.1419. Min Act: -0.0000

Data Index: 615786 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 4.7882. Min Range: -4.7882

Max Act: 4.2109. Min Act: -0.0000

Data Index: 666435 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.9739. Min Act: -0.0000

Data Index: 395573 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.9112. Min Act: -0.0000

Data Index: 885564 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.8819. Min Act: -0.0000

Data Index: 647778 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.9872. Min Act: -0.0000

Data Index: 371426 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 4.7882. Min Range: -4.7882

Max Act: 4.0134. Min Act: -0.0000

Data Index: 123749 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.5483. Min Act: -0.0000

Data Index: 626396 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.4866. Min Act: -0.0000

Data Index: 77191 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.5683. Min Act: -0.0000

Data Index: 1201287 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.7307. Min Act: -0.0000

Data Index: 1296943 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.5281. Min Act: -0.0000

Data Index: 973689 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.4469. Min Act: -0.0000

Data Index: 281963 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.2494. Min Act: -0.0000

Data Index: 1314093 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.3887. Min Act: -0.0000

Data Index: 886039 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.3223. Min Act: -0.0000

Data Index: 147128 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.4490. Min Act: -0.0000

Data Index: 681301 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 4.7882. Min Range: -4.7882

Max Act: 3.2593. Min Act: -0.0000

Data Index: 139087 (C4 (Web Text))

Max Activating Token Index: 56