Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2871 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.7070. Min Act: -0.0000

Data Index: 532950 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6402. Min Act: -0.0000

Data Index: 58598 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6457. Min Act: -0.0000

Data Index: 665115 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5606. Min Act: -0.0000

Data Index: 861075 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5682. Min Act: -0.0000

Data Index: 664458 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5564. Min Act: -0.0000

Data Index: 121583 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4942. Min Act: -0.0000

Data Index: 250210 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1293049 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4633. Min Act: -0.0000

Data Index: 669781 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4468. Min Act: -0.0000

Data Index: 483538 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4528. Min Act: -0.0000

Data Index: 142150 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4847. Min Act: -0.0000

Data Index: 978988 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4697. Min Act: -0.0000

Data Index: 916987 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4062. Min Act: -0.0000

Data Index: 656077 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4090. Min Act: -0.0000

Data Index: 117870 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1113113 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.3810. Min Act: -0.0000

Data Index: 20532 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1153225 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.3619. Min Act: -0.0000

Data Index: 261234 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.3888. Min Act: -0.0000

Data Index: 281248 (C4 (Web Text))

Max Activating Token Index: 883