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

Dataset: The Pile

Neuron 2100 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1277417 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4576. Min Act: -0.0000

Data Index: 810141 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1236807 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4813. Min Act: -0.0000

Data Index: 419125 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1433273 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1070016 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1677856 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4070. Min Act: -0.0000

Data Index: 298592 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4120. Min Act: -0.0000

Data Index: 88246 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1835266 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4020. Min Act: -0.0000

Data Index: 652603 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1208455 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3786. Min Act: -0.0000

Data Index: 910693 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3806. Min Act: -0.0000

Data Index: 643337 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1307293 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1312684 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4038. Min Act: -0.0000

Data Index: 948962 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3895. Min Act: -0.0000

Data Index: 294073 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3896. Min Act: -0.0000

Data Index: 481111 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1470435 (The Pile)

Max Activating Token Index: 739