Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2316 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1031. Min Act: -0.0001

Data Index: 420674 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1003. Min Act: -0.0001

Data Index: 850937 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0977. Min Act: -0.0001

Data Index: 431491 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1019. Min Act: -0.0001

Data Index: 838443 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1472438 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0952. Min Act: -0.0001

Data Index: 864568 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1119568 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1226218 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0894. Min Act: -0.0001

Data Index: 658643 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0936. Min Act: -0.0001

Data Index: 443022 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0912. Min Act: -0.0001

Data Index: 107288 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1549323 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1441105 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0862. Min Act: -0.0001

Data Index: 344269 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1584734 (Python Code)

Max Activating Token Index: 664

Text #15

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0882. Min Act: -0.0001

Data Index: 393425 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1656311 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1558276 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0850. Min Act: -0.0001

Data Index: 208257 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1395376 (Python Code)

Max Activating Token Index: 357