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

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

Neuron 5514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.8510. Min Act: -0.0001

Data Index: 884720 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.6930. Min Act: -0.0001

Data Index: 647715 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.5664. Min Act: -0.0001

Data Index: 1318022 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.5993. Min Act: -0.0001

Data Index: 449207 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3865. Min Act: -0.0001

Data Index: 1243249 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4756. Min Act: -0.0001

Data Index: 1314242 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3948. Min Act: -0.0001

Data Index: 435433 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4341. Min Act: -0.0001

Data Index: 167614 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3949. Min Act: -0.0001

Data Index: 26558 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4428. Min Act: -0.0001

Data Index: 1248473 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3512. Min Act: -0.0001

Data Index: 1054717 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4146. Min Act: -0.0001

Data Index: 1281435 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.1464. Min Act: -0.0001

Data Index: 711183 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3937. Min Act: -0.0001

Data Index: 881809 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3782. Min Act: -0.0001

Data Index: 494530 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4574. Min Act: -0.0001

Data Index: 1716 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4388. Min Act: -0.0001

Data Index: 1016842 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.3552. Min Act: -0.0001

Data Index: 1033598 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.2789. Min Act: -0.0001

Data Index: 456113 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.8510. Min Range: -1.8510

Max Act: 1.4285. Min Act: -0.0001

Data Index: 565980 (C4 (Web Text))

Max Activating Token Index: 978