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

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

Neuron 6043 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.7741. Min Act: -0.0000

Data Index: 573045 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.4734. Min Act: -0.0000

Data Index: 139502 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.1573. Min Act: -0.0000

Data Index: 893641 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.1696. Min Act: -0.0000

Data Index: 189436 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.0196. Min Act: -0.0000

Data Index: 1134408 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1079011 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.3879. Min Act: -0.0000

Data Index: 987752 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.3673. Min Act: -0.0000

Data Index: 921711 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.1565. Min Act: -0.0000

Data Index: 677445 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.0739. Min Act: -0.0000

Data Index: 1340997 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1284593 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8764. Min Act: -0.0000

Data Index: 561325 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8530. Min Act: -0.0000

Data Index: 306937 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.9632. Min Act: -0.0000

Data Index: 44931 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.9178. Min Act: -0.0000

Data Index: 854640 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 2.4734. Min Range: -2.4734

Max Act: 2.0314. Min Act: -0.0000

Data Index: 121125 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.7982. Min Act: -0.0000

Data Index: 200115 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.7942. Min Act: -0.0000

Data Index: 393009 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.7937. Min Act: -0.0000

Data Index: 993650 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.4734. Min Range: -2.4734

Max Act: 1.8937. Min Act: -0.0000

Data Index: 160045 (C4 (Web Text))

Max Activating Token Index: 891