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

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

Neuron 2839 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.5980. Min Act: -0.0000

Data Index: 646700 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1084559 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1196109 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1113574 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2743. Min Act: -0.0000

Data Index: 463754 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1430. Min Act: -0.0000

Data Index: 873941 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1220006 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1256797 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1097751 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0310. Min Act: -0.0000

Data Index: 865884 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0077. Min Act: -0.0000

Data Index: 866614 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1092442 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0078. Min Act: -0.0000

Data Index: 551548 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0103. Min Act: -0.0000

Data Index: 105038 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9915. Min Act: -0.0000

Data Index: 790260 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9757. Min Act: -0.0000

Data Index: 526910 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.8630. Min Act: -0.0000

Data Index: 674258 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.8453. Min Act: -0.0000

Data Index: 948643 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9022. Min Act: -0.0000

Data Index: 247758 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9008. Min Act: -0.0000

Data Index: 173845 (C4 (Web Text))

Max Activating Token Index: 196