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

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

Neuron 599 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8470. Min Act: -0.0001

Data Index: 567488 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8710. Min Act: -0.0001

Data Index: 645891 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8652. Min Act: -0.0001

Data Index: 142702 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8515. Min Act: -0.0001

Data Index: 208603 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7713. Min Act: -0.0001

Data Index: 235485 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8234. Min Act: -0.0001

Data Index: 810352 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7834. Min Act: -0.0001

Data Index: 306624 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7739. Min Act: -0.0001

Data Index: 550905 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.8106. Min Act: -0.0001

Data Index: 388843 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7733. Min Act: -0.0001

Data Index: 1332452 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7931. Min Act: -0.0001

Data Index: 492800 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7571. Min Act: -0.0001

Data Index: 336130 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7557. Min Act: -0.0001

Data Index: 727478 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7648. Min Act: -0.0001

Data Index: 829016 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7612. Min Act: -0.0001

Data Index: 226358 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7460. Min Act: -0.0001

Data Index: 865764 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7369. Min Act: -0.0001

Data Index: 38833 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1555183 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7328. Min Act: -0.0001

Data Index: 987912 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.8710. Min Range: -0.8710

Max Act: 0.7088. Min Act: -0.0001

Data Index: 1197090 (C4 (Web Text))

Max Activating Token Index: 405