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

Dataset: The Pile

Neuron 4476 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.9210. Min Act: -0.0000

Data Index: 131855 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 10.3197. Min Range: -10.3197

Max Act: 10.3197. Min Act: -0.0000

Data Index: 196764 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.9971. Min Act: -0.0000

Data Index: 600015 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 10.3197. Min Range: -10.3197

Max Act: 10.0133. Min Act: -0.0000

Data Index: 1039547 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 10.3197. Min Range: -10.3197

Max Act: 10.0051. Min Act: -0.0000

Data Index: 1782337 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.5491. Min Act: -0.0000

Data Index: 1479141 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.4771. Min Act: -0.0000

Data Index: 1700192 (The Pile)

Max Activating Token Index: 719

Text #7

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.3874. Min Act: -0.0000

Data Index: 850017 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.4693. Min Act: -0.0000

Data Index: 1063158 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.6211. Min Act: -0.0000

Data Index: 23552 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.4870. Min Act: -0.0000

Data Index: 396233 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.0579. Min Act: -0.0000

Data Index: 1650276 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.5107. Min Act: -0.0000

Data Index: 1093745 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.3274. Min Act: -0.0000

Data Index: 949289 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.2135. Min Act: -0.0000

Data Index: 1531044 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 10.3197. Min Range: -10.3197

Max Act: 8.9631. Min Act: -0.0000

Data Index: 1258963 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.0760. Min Act: -0.0000

Data Index: 673177 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 10.3197. Min Range: -10.3197

Max Act: 8.9960. Min Act: -0.0000

Data Index: 595162 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 10.3197. Min Range: -10.3197

Max Act: 8.6476. Min Act: -0.0000

Data Index: 934304 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 10.3197. Min Range: -10.3197

Max Act: 9.3979. Min Act: -0.0000

Data Index: 392159 (The Pile)

Max Activating Token Index: 264