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

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

Neuron 3100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.2557. Min Act: -0.0001

Data Index: 193610 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.6408. Min Act: -0.0000

Data Index: 1236330 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.6761. Min Range: -3.6761

Max Act: 2.7570. Min Act: -0.0000

Data Index: 648698 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.6761. Min Act: -0.0000

Data Index: 269671 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5449. Min Act: -0.0000

Data Index: 1023225 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.6034. Min Act: -0.0001

Data Index: 1296098 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.1122. Min Act: -0.0000

Data Index: 213856 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.3593. Min Act: -0.0000

Data Index: 1245853 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.0460. Min Act: -0.0000

Data Index: 1202829 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.3049. Min Act: -0.0000

Data Index: 182880 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.0161. Min Act: -0.0000

Data Index: 822052 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.0265. Min Act: -0.0000

Data Index: 966393 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.6761. Min Range: -3.6761

Max Act: 2.9307. Min Act: -0.0001

Data Index: 533719 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 3.6761. Min Range: -3.6761

Max Act: 2.9894. Min Act: -0.0001

Data Index: 256864 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.5032. Min Act: -0.0000

Data Index: 1102597 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.6761. Min Range: -3.6761

Max Act: 2.8008. Min Act: -0.0000

Data Index: 561987 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.1952. Min Act: -0.0000

Data Index: 775220 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 3.6761. Min Range: -3.6761

Max Act: 2.4899. Min Act: -0.0000

Data Index: 198558 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 3.6761. Min Range: -3.6761

Max Act: 2.8652. Min Act: -0.0000

Data Index: 256182 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 3.6761. Min Range: -3.6761

Max Act: 3.1953. Min Act: -0.0000

Data Index: 192340 (C4 (Web Text))

Max Activating Token Index: 968