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

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

Neuron 2017 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: 0.6673. Min Range: -0.6673

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1234655 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1047531 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.6025. Min Act: -0.0001

Data Index: 1178812 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5835. Min Act: -0.0001

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5788. Min Act: -0.0001

Data Index: 48066 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5407. Min Act: -0.0001

Data Index: 646699 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5483. Min Act: -0.0001

Data Index: 1289685 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5100. Min Act: -0.0001

Data Index: 37548 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5917. Min Act: -0.0001

Data Index: 861923 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5526. Min Act: -0.0001

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5577. Min Act: -0.0001

Data Index: 698604 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5549. Min Act: -0.0001

Data Index: 1321337 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5209. Min Act: -0.0001

Data Index: 211628 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5574. Min Act: -0.0001

Data Index: 224148 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5533. Min Act: -0.0001

Data Index: 509522 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5496. Min Act: -0.0001

Data Index: 422522 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5281. Min Act: -0.0001

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4949. Min Act: -0.0001

Data Index: 1049403 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5404. Min Act: -0.0001

Data Index: 25446 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5395. Min Act: -0.0001

Data Index: 119462 (C4 (Web Text))

Max Activating Token Index: 138