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

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

Neuron 1644 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4726. Min Act: -0.0001

Data Index: 511085 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4748. Min Act: -0.0001

Data Index: 30865 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4670. Min Act: -0.0001

Data Index: 675765 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4439. Min Act: -0.0001

Data Index: 893500 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1213757 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4585. Min Act: -0.0001

Data Index: 431075 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1249002 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4023. Min Act: -0.0001

Data Index: 965873 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3945. Min Act: -0.0001

Data Index: 345848 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4245. Min Act: -0.0001

Data Index: 140431 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3958. Min Act: -0.0001

Data Index: 479540 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3790. Min Act: -0.0001

Data Index: 661241 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3836. Min Act: -0.0001

Data Index: 167484 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4189. Min Act: -0.0001

Data Index: 719664 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3887. Min Act: -0.0001

Data Index: 63486 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4277. Min Act: -0.0001

Data Index: 1133980 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3855. Min Act: -0.0001

Data Index: 790648 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1352694 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3943. Min Act: -0.0001

Data Index: 900874 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3832. Min Act: -0.0001

Data Index: 1340998 (C4 (Web Text))

Max Activating Token Index: 162