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

Dataset: The Pile

Neuron 4052 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1163264 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7560. Min Act: -0.0000

Data Index: 139495 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6811. Min Act: -0.0000

Data Index: 647091 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1047506 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6197. Min Act: -0.0000

Data Index: 566085 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7157. Min Act: -0.0000

Data Index: 967434 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1245581 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6246. Min Act: -0.0000

Data Index: 986199 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1669368 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6479. Min Act: -0.0000

Data Index: 607773 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1605472 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6713. Min Act: -0.0000

Data Index: 262271 (The Pile)

Max Activating Token Index: 723

Text #12

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1353078 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5746. Min Act: -0.0000

Data Index: 703580 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1374256 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5854. Min Act: -0.0001

Data Index: 314543 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1534546 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1700905 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.5341. Min Act: -0.0000

Data Index: 319475 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6632. Min Act: -0.0001

Data Index: 800119 (The Pile)

Max Activating Token Index: 384