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

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

Neuron 2306 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: 3.4443. Min Range: -3.4443

Max Act: 3.4443. Min Act: -0.0001

Data Index: 905796 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3722. Min Act: -0.0001

Data Index: 1025431 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3301. Min Act: -0.0001

Data Index: 297007 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.0337. Min Act: -0.0000

Data Index: 1034939 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.9743. Min Act: -0.0000

Data Index: 334965 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.6823. Min Act: -0.0000

Data Index: 538313 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.7360. Min Act: -0.0000

Data Index: 945102 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1323809 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.9276. Min Act: -0.0000

Data Index: 646346 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.9331. Min Act: -0.0000

Data Index: 333288 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.6805. Min Act: -0.0001

Data Index: 771605 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.4026. Min Act: -0.0001

Data Index: 186287 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.5691. Min Act: -0.0000

Data Index: 1136711 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.6076. Min Act: -0.0000

Data Index: 159823 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.4734. Min Act: -0.0001

Data Index: 639076 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.5845. Min Act: -0.0000

Data Index: 564342 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.5929. Min Act: -0.0001

Data Index: 561300 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.6784. Min Act: -0.0001

Data Index: 822060 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.6758. Min Act: -0.0000

Data Index: 769945 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.4443. Min Range: -3.4443

Max Act: 2.5298. Min Act: -0.0000

Data Index: 861675 (C4 (Web Text))

Max Activating Token Index: 193