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

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

Neuron 1870 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.6565. Min Act: -0.0001

Data Index: 1064495 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.7397. Min Act: -0.0001

Data Index: 22009 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.4968. Min Act: -0.0001

Data Index: 1069955 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.4308. Min Act: -0.0001

Data Index: 182278 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.3684. Min Act: -0.0001

Data Index: 2121 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.3883. Min Act: -0.0001

Data Index: 1088092 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.3828. Min Act: -0.0001

Data Index: 1326086 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.3404. Min Act: -0.0001

Data Index: 287681 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1991. Min Act: -0.0001

Data Index: 822098 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.3027. Min Act: -0.0001

Data Index: 480097 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2456. Min Act: -0.0001

Data Index: 589380 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.3735. Min Act: -0.0001

Data Index: 307046 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2976. Min Act: -0.0001

Data Index: 753086 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1670. Min Act: -0.0001

Data Index: 899117 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2783. Min Act: -0.0001

Data Index: 954683 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1529. Min Act: -0.0001

Data Index: 170565 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2069. Min Act: -0.0001

Data Index: 965313 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1369. Min Act: -0.0001

Data Index: 84864 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1462. Min Act: -0.0001

Data Index: 235275 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1343. Min Act: -0.0001

Data Index: 457200 (C4 (Web Text))

Max Activating Token Index: 11