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

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

Neuron 1185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1569835 (Python Code)

Max Activating Token Index: 643

Text #1

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1411984 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1532993 (Python Code)

Max Activating Token Index: 375

Text #3

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1416119 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1426361 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1433988 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1511395 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1562512 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1473496 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1483709 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1519962 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1654154 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1443296 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1495289 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1496687 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1554616 (Python Code)

Max Activating Token Index: 745

Text #16

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1364946 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1637507 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1490776 (Python Code)

Max Activating Token Index: 119

Text #19

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1600851 (Python Code)

Max Activating Token Index: 280