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

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

Neuron 4639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.3575. Min Act: -0.0000

Data Index: 6446 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.1791. Min Act: -0.0000

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.9364. Min Act: -0.0000

Data Index: 1146864 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.1698. Min Act: -0.0000

Data Index: 468877 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.1009. Min Act: -0.0000

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.1083. Min Act: -0.0000

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7942. Min Act: -0.0000

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.8804. Min Act: -0.0000

Data Index: 655387 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7591. Min Act: -0.0000

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1354143 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.8022. Min Act: -0.0000

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7934. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6140. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7543. Min Act: -0.0000

Data Index: 1250463 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7050. Min Act: -0.0000

Data Index: 993422 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7163. Min Act: -0.0000

Data Index: 1188800 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6030. Min Act: -0.0000

Data Index: 535525 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.5938. Min Act: -0.0000

Data Index: 969610 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.5874. Min Act: -0.0000

Data Index: 1082189 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.4955. Min Act: -0.0000

Data Index: 476059 (C4 (Web Text))

Max Activating Token Index: 43