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

Dataset: The Pile

Neuron 1679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1499137 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.2881. Min Act: -0.0000

Data Index: 968032 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.8985. Min Act: -0.0000

Data Index: 256809 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0438. Min Act: -0.0000

Data Index: 271970 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.8720. Min Act: -0.0000

Data Index: 1967548 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7942. Min Act: -0.0000

Data Index: 269086 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7847. Min Act: -0.0000

Data Index: 516860 (The Pile)

Max Activating Token Index: 365

Text #7

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.9198. Min Act: -0.0000

Data Index: 1163894 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.8905. Min Act: -0.0000

Data Index: 445881 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.8548. Min Act: -0.0000

Data Index: 670329 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7236. Min Act: -0.0000

Data Index: 1536988 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.6839. Min Act: -0.0000

Data Index: 1815041 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.6949. Min Act: -0.0000

Data Index: 1713758 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.6923. Min Act: -0.0000

Data Index: 1994023 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.9683. Min Act: -0.0000

Data Index: 418033 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.8086. Min Act: -0.0000

Data Index: 120325 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7835. Min Act: -0.0000

Data Index: 742491 (The Pile)

Max Activating Token Index: 298

Text #17

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7552. Min Act: -0.0000

Data Index: 898604 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7668. Min Act: -0.0000

Data Index: 1198296 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 3.2881. Min Range: -3.2881

Max Act: 2.7401. Min Act: -0.0000

Data Index: 447175 (The Pile)

Max Activating Token Index: 825