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

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

Neuron 4176 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: 1.2091. Min Range: -1.2091

Max Act: 1.0623. Min Act: -0.0001

Data Index: 240977 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 1.2091. Min Range: -1.2091

Max Act: 1.2091. Min Act: -0.0001

Data Index: 387750 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.2091. Min Range: -1.2091

Max Act: 1.0042. Min Act: -0.0001

Data Index: 662380 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.2091. Min Range: -1.2091

Max Act: 1.1000. Min Act: -0.0001

Data Index: 973673 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.2091. Min Range: -1.2091

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1310607 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.2091. Min Range: -1.2091

Max Act: 1.1397. Min Act: -0.0001

Data Index: 159106 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 1.2091. Min Range: -1.2091

Max Act: 1.0350. Min Act: -0.0001

Data Index: 86438 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9975. Min Act: -0.0001

Data Index: 1042598 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9538. Min Act: -0.0001

Data Index: 672573 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9806. Min Act: -0.0001

Data Index: 896652 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9633. Min Act: -0.0001

Data Index: 1069577 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9631. Min Act: -0.0001

Data Index: 847865 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9036. Min Act: -0.0001

Data Index: 150727 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9707. Min Act: -0.0001

Data Index: 33566 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9081. Min Act: -0.0001

Data Index: 498631 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9299. Min Act: -0.0001

Data Index: 425352 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.8000. Min Act: -0.0001

Data Index: 1116300 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.8325. Min Act: -0.0001

Data Index: 109151 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.8959. Min Act: -0.0001

Data Index: 802217 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.2091. Min Range: -1.2091

Max Act: 0.9279. Min Act: -0.0001

Data Index: 58015 (C4 (Web Text))

Max Activating Token Index: 837