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

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

Neuron 1239 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.7501. Min Act: -0.0001

Data Index: 896959 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3862. Min Act: -0.0001

Data Index: 640341 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3503. Min Act: -0.0001

Data Index: 232793 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3704. Min Act: -0.0001

Data Index: 409631 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3303. Min Act: -0.0000

Data Index: 357420 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3368. Min Act: -0.0001

Data Index: 550040 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3518. Min Act: -0.0001

Data Index: 544303 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3472. Min Act: -0.0001

Data Index: 540011 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3554. Min Act: -0.0001

Data Index: 946940 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3415. Min Act: -0.0001

Data Index: 436549 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3781. Min Act: -0.0001

Data Index: 302421 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3095. Min Act: -0.0001

Data Index: 82225 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2936. Min Act: -0.0000

Data Index: 688095 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2984. Min Act: -0.0001

Data Index: 725473 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2988. Min Act: -0.0001

Data Index: 232069 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2900. Min Act: -0.0001

Data Index: 179195 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.3041. Min Act: -0.0001

Data Index: 439675 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2890. Min Act: -0.0001

Data Index: 246501 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2893. Min Act: -0.0001

Data Index: 974463 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.2835. Min Act: -0.0001

Data Index: 623555 (C4 (Web Text))

Max Activating Token Index: 1020