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

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

Neuron 2774 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: 1.2641. Min Range: -1.2641

Max Act: 1.2641. Min Act: -0.0001

Data Index: 311784 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8620. Min Act: -0.0001

Data Index: 1384947 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8554. Min Act: -0.0001

Data Index: 261440 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8832. Min Act: -0.0001

Data Index: 1065531 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7767. Min Act: -0.0001

Data Index: 102371 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1385531 (Python Code)

Max Activating Token Index: 841

Text #6

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1559630 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7774. Min Act: -0.0001

Data Index: 297954 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7666. Min Act: -0.0001

Data Index: 1377749 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7254. Min Act: -0.0001

Data Index: 713477 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7099. Min Act: -0.0001

Data Index: 815814 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1498997 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7764. Min Act: -0.0001

Data Index: 30891 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7182. Min Act: -0.0001

Data Index: 1419789 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1554122 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1224140 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7207. Min Act: -0.0001

Data Index: 145991 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1383776 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.6805. Min Act: -0.0001

Data Index: 1131540 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1527068 (Python Code)

Max Activating Token Index: 179