Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3803 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2951. Min Act: -0.0001

Data Index: 19096 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1480829 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2882. Min Act: -0.0002

Data Index: 409199 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2907. Min Act: -0.0001

Data Index: 1471862 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2930. Min Act: -0.0001

Data Index: 1423213 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1467907 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1501111 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1369752 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2579. Min Act: -0.0001

Data Index: 1624663 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2737. Min Act: -0.0001

Data Index: 1567515 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2723. Min Act: -0.0002

Data Index: 312985 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2648. Min Act: -0.0001

Data Index: 1501579 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1478530 (Python Code)

Max Activating Token Index: 787

Text #13

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2740. Min Act: -0.0001

Data Index: 753485 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2715. Min Act: -0.0002

Data Index: 1408987 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2698. Min Act: -0.0001

Data Index: 1562816 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1446052 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2906. Min Act: -0.0001

Data Index: 88933 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1622155 (Python Code)

Max Activating Token Index: 184

Text #19

Max Range: 0.3131. Min Range: -0.3131

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1366576 (Python Code)

Max Activating Token Index: 776