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

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

Neuron 4010 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: 1.4088. Min Range: -1.4088

Max Act: 1.4088. Min Act: -0.0001

Data Index: 337892 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.2076. Min Act: -0.0001

Data Index: 963831 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.2044. Min Act: -0.0000

Data Index: 529710 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0723. Min Act: -0.0000

Data Index: 156915 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0742. Min Act: -0.0001

Data Index: 1087368 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0367. Min Act: -0.0001

Data Index: 915175 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0377. Min Act: -0.0001

Data Index: 488912 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0719. Min Act: -0.0001

Data Index: 799452 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0599. Min Act: -0.0001

Data Index: 280020 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.1195. Min Act: -0.0001

Data Index: 1083072 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0534. Min Act: -0.0001

Data Index: 424963 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0218. Min Act: -0.0001

Data Index: 564582 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0297. Min Act: -0.0001

Data Index: 57919 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0285. Min Act: -0.0001

Data Index: 144048 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0093. Min Act: -0.0001

Data Index: 435215 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.4088. Min Range: -1.4088

Max Act: 1.0362. Min Act: -0.0000

Data Index: 514216 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 1.4088. Min Range: -1.4088

Max Act: 0.9766. Min Act: -0.0000

Data Index: 378014 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.4088. Min Range: -1.4088

Max Act: 0.9877. Min Act: -0.0001

Data Index: 845064 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.4088. Min Range: -1.4088

Max Act: 0.9505. Min Act: -0.0001

Data Index: 373892 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.4088. Min Range: -1.4088

Max Act: 0.9813. Min Act: -0.0001

Data Index: 710608 (C4 (Web Text))

Max Activating Token Index: 636