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

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

Neuron 1962 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.6397. Min Act: -0.0000

Data Index: 709308 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.7937. Min Act: -0.0000

Data Index: 966801 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2156. Min Act: -0.0000

Data Index: 972335 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.7598. Min Act: -0.0000

Data Index: 1246045 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2325. Min Act: -0.0000

Data Index: 804400 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2390. Min Act: -0.0000

Data Index: 1307666 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.4586. Min Act: -0.0000

Data Index: 48667 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1330. Min Act: -0.0000

Data Index: 956584 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2602. Min Act: -0.0001

Data Index: 1313061 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2505. Min Act: -0.0000

Data Index: 161574 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.3983. Min Act: -0.0000

Data Index: 323539 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2276. Min Act: -0.0000

Data Index: 1225142 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.2245. Min Act: -0.0001

Data Index: 240591 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1909. Min Act: -0.0000

Data Index: 776261 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1641. Min Act: -0.0000

Data Index: 496429 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.9043. Min Act: -0.0000

Data Index: 1176025 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.0030. Min Act: -0.0000

Data Index: 922256 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 3.7937. Min Range: -3.7937

Max Act: 2.9765. Min Act: -0.0000

Data Index: 650010 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.0993. Min Act: -0.0000

Data Index: 67818 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 3.7937. Min Range: -3.7937

Max Act: 3.1941. Min Act: -0.0000

Data Index: 669895 (C4 (Web Text))

Max Activating Token Index: 626