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

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

Neuron 5167 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: 3.9307. Min Range: -3.9307

Max Act: 3.9307. Min Act: -0.0001

Data Index: 415958 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.7900. Min Act: -0.0001

Data Index: 544209 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.7399. Min Act: -0.0001

Data Index: 1050447 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.5231. Min Act: -0.0001

Data Index: 101328 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.1411. Min Act: -0.0001

Data Index: 788588 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.5641. Min Act: -0.0001

Data Index: 522234 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.1990. Min Act: -0.0001

Data Index: 223991 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.3487. Min Act: -0.0001

Data Index: 1109510 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.0270. Min Act: -0.0001

Data Index: 669009 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.0175. Min Act: -0.0001

Data Index: 1310217 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.5653. Min Act: -0.0001

Data Index: 572335 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.0610. Min Act: -0.0001

Data Index: 1300931 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 3.9307. Min Range: -3.9307

Max Act: 2.9406. Min Act: -0.0001

Data Index: 918306 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.1676. Min Act: -0.0001

Data Index: 888788 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.2507. Min Act: -0.0001

Data Index: 901065 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.0750. Min Act: -0.0001

Data Index: 30704 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.3564. Min Act: -0.0001

Data Index: 18801 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.0519. Min Act: -0.0001

Data Index: 1174288 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.9307. Min Range: -3.9307

Max Act: 3.0327. Min Act: -0.0001

Data Index: 1322475 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 3.9307. Min Range: -3.9307

Max Act: 2.7201. Min Act: -0.0001

Data Index: 1221176 (C4 (Web Text))

Max Activating Token Index: 904