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

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

Neuron 2862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8991. Min Act: -0.0000

Data Index: 575274 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8913. Min Act: -0.0001

Data Index: 1249369 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1257055 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8973. Min Act: -0.0001

Data Index: 703732 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8740. Min Act: -0.0001

Data Index: 368895 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8552. Min Act: -0.0001

Data Index: 697455 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1164511 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8335. Min Act: -0.0000

Data Index: 938033 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8492. Min Act: -0.0001

Data Index: 840110 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1040403 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8340. Min Act: -0.0001

Data Index: 617022 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8356. Min Act: -0.0000

Data Index: 807504 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1030363 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1270374 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7840. Min Act: -0.0001

Data Index: 907060 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7714. Min Act: -0.0001

Data Index: 865609 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7743. Min Act: -0.0001

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7731. Min Act: -0.0001

Data Index: 738683 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7664. Min Act: -0.0000

Data Index: 619480 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7401. Min Act: -0.0001

Data Index: 243114 (C4 (Web Text))

Max Activating Token Index: 1006