Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4133 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.9933. Min Act: -0.0001

Data Index: 702996 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.9244. Min Act: -0.0001

Data Index: 986338 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.9100. Min Act: -0.0001

Data Index: 88650 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.8786. Min Act: -0.0001

Data Index: 444022 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.8410. Min Act: -0.0001

Data Index: 495197 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.8112. Min Act: -0.0001

Data Index: 383131 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.8123. Min Act: -0.0001

Data Index: 576972 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7010. Min Act: -0.0001

Data Index: 994028 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7669. Min Act: -0.0001

Data Index: 374380 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7697. Min Act: -0.0001

Data Index: 138874 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.8167. Min Act: -0.0001

Data Index: 864501 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7377. Min Act: -0.0001

Data Index: 567489 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7172. Min Act: -0.0001

Data Index: 671810 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1099052 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1090964 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7331. Min Act: -0.0001

Data Index: 636992 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.6765. Min Act: -0.0001

Data Index: 7235 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7179. Min Act: -0.0001

Data Index: 1067635 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7280. Min Act: -0.0001

Data Index: 396536 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.9933. Min Range: -0.9933

Max Act: 0.7632. Min Act: -0.0001

Data Index: 835500 (C4 (Web Text))

Max Activating Token Index: 267