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

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

Neuron 7 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3950. Min Range: -4.3950

Max Act: 4.3950. Min Act: -0.0000

Data Index: 30933 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 4.3950. Min Range: -4.3950

Max Act: 4.1060. Min Act: -0.0000

Data Index: 405703 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 4.3950. Min Range: -4.3950

Max Act: 4.1027. Min Act: -0.0000

Data Index: 620022 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 4.3950. Min Range: -4.3950

Max Act: 4.0307. Min Act: -0.0000

Data Index: 936603 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.7288. Min Act: -0.0000

Data Index: 396687 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.5984. Min Act: -0.0000

Data Index: 661653 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.8837. Min Act: -0.0000

Data Index: 675684 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.5943. Min Act: -0.0000

Data Index: 617504 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.8725. Min Act: -0.0000

Data Index: 950761 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.3303. Min Act: -0.0000

Data Index: 1089650 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.4347. Min Act: -0.0000

Data Index: 1298277 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.5748. Min Act: -0.0000

Data Index: 1026304 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.3765. Min Act: -0.0000

Data Index: 817058 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.3615. Min Act: -0.0000

Data Index: 998308 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.5432. Min Act: -0.0000

Data Index: 29670 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.3262. Min Act: -0.0000

Data Index: 138383 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.2796. Min Act: -0.0000

Data Index: 770924 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 4.3950. Min Range: -4.3950

Max Act: 2.9325. Min Act: -0.0000

Data Index: 1187717 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.3081. Min Act: -0.0000

Data Index: 1129520 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 4.3950. Min Range: -4.3950

Max Act: 3.3209. Min Act: -0.0000

Data Index: 679054 (C4 (Web Text))

Max Activating Token Index: 446