Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1648 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.6685. Min Act: -0.0001

Data Index: 819776 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1085348 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1327815 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.6102. Min Act: -0.0001

Data Index: 108192 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.5399. Min Act: -0.0001

Data Index: 74045 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4754. Min Act: -0.0001

Data Index: 18353 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4424. Min Act: -0.0001

Data Index: 410975 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4877. Min Act: -0.0001

Data Index: 215592 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4101. Min Act: -0.0001

Data Index: 138713 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3901. Min Act: -0.0001

Data Index: 213406 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3752. Min Act: -0.0001

Data Index: 697666 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3604. Min Act: -0.0001

Data Index: 515880 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3793. Min Act: -0.0001

Data Index: 378519 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4023. Min Act: -0.0001

Data Index: 302376 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1205042 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3857. Min Act: -0.0001

Data Index: 537540 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.4308. Min Act: -0.0001

Data Index: 80297 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3944. Min Act: -0.0001

Data Index: 513148 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3785. Min Act: -0.0001

Data Index: 816708 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.6685. Min Range: -0.6685

Max Act: 0.3831. Min Act: -0.0001

Data Index: 706186 (C4 (Web Text))

Max Activating Token Index: 545