Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2939 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1072781 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.5575. Min Act: -0.0001

Data Index: 1091233 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.5055. Min Act: -0.0001

Data Index: 410530 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1437915 (Python Code)

Max Activating Token Index: 904

Text #4

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4085. Min Act: -0.0001

Data Index: 507316 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.5063. Min Act: -0.0001

Data Index: 1351481 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4901. Min Act: -0.0001

Data Index: 61161 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4877. Min Act: -0.0001

Data Index: 735872 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4619. Min Act: -0.0001

Data Index: 1352556 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4733. Min Act: -0.0001

Data Index: 4034 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4900. Min Act: -0.0001

Data Index: 89700 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4808. Min Act: -0.0001

Data Index: 3689 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4330. Min Act: -0.0001

Data Index: 619149 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4625. Min Act: -0.0001

Data Index: 967404 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4771. Min Act: -0.0001

Data Index: 716569 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4083. Min Act: -0.0001

Data Index: 826429 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4555. Min Act: -0.0001

Data Index: 303961 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4641. Min Act: -0.0001

Data Index: 1240702 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4600. Min Act: -0.0001

Data Index: 362375 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.6099. Min Range: -0.6099

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1073033 (C4 (Web Text))

Max Activating Token Index: 461