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

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

Neuron 2635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3185. Min Range: -2.3185

Max Act: 2.3185. Min Act: -0.0000

Data Index: 163697 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 2.3185. Min Range: -2.3185

Max Act: 2.0778. Min Act: -0.0000

Data Index: 150707 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.8609. Min Act: -0.0000

Data Index: 1163831 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.7405. Min Act: -0.0000

Data Index: 319413 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.7151. Min Act: -0.0000

Data Index: 333025 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.6819. Min Act: -0.0001

Data Index: 1163547 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.6020. Min Act: -0.0000

Data Index: 789207 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.5709. Min Act: -0.0000

Data Index: 254236 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.5559. Min Act: -0.0000

Data Index: 742003 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1943 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.4133. Min Act: -0.0000

Data Index: 671864 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.4737. Min Act: -0.0000

Data Index: 366250 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.4038. Min Act: -0.0000

Data Index: 938942 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.3229. Min Act: -0.0000

Data Index: 645474 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.3883. Min Act: -0.0000

Data Index: 345096 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.3672. Min Act: -0.0001

Data Index: 1214940 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.4231. Min Act: -0.0001

Data Index: 110337 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.3747. Min Act: -0.0001

Data Index: 979095 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.2489. Min Act: -0.0001

Data Index: 236154 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 2.3185. Min Range: -2.3185

Max Act: 1.1809. Min Act: -0.0001

Data Index: 117339 (C4 (Web Text))

Max Activating Token Index: 574