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

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

Neuron 587 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: 1.4001. Min Range: -1.4001

Max Act: 1.3100. Min Act: -0.0000

Data Index: 430381 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.4001. Min Act: -0.0001

Data Index: 119815 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1355853 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.2348. Min Act: -0.0000

Data Index: 375502 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1713. Min Act: -0.0000

Data Index: 197121 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1795. Min Act: -0.0001

Data Index: 907814 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1208270 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1522. Min Act: -0.0001

Data Index: 473687 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1887. Min Act: -0.0001

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1459. Min Act: -0.0001

Data Index: 689612 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1055. Min Act: -0.0001

Data Index: 856834 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0439. Min Act: -0.0001

Data Index: 396045 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1041. Min Act: -0.0001

Data Index: 774627 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1007. Min Act: -0.0001

Data Index: 276903 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.1273. Min Act: -0.0000

Data Index: 438614 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0981. Min Act: -0.0000

Data Index: 951074 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0485. Min Act: -0.0000

Data Index: 770442 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0673. Min Act: -0.0001

Data Index: 36292 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0471. Min Act: -0.0001

Data Index: 35111 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.4001. Min Range: -1.4001

Max Act: 1.0750. Min Act: -0.0001

Data Index: 1093784 (C4 (Web Text))

Max Activating Token Index: 163