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

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

Neuron 2262 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: 3.7073. Min Range: -3.7073

Max Act: 3.4904. Min Act: -0.0000

Data Index: 294054 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4766. Min Act: -0.0000

Data Index: 353861 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4361. Min Act: -0.0000

Data Index: 114924 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4242. Min Act: -0.0000

Data Index: 31701 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5632. Min Act: -0.0000

Data Index: 922256 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4441. Min Act: -0.0000

Data Index: 760059 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5790. Min Act: -0.0000

Data Index: 1338254 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5635. Min Act: -0.0000

Data Index: 723447 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.7073. Min Act: -0.0000

Data Index: 293777 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5174. Min Act: -0.0000

Data Index: 401587 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4674. Min Act: -0.0000

Data Index: 412879 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4580. Min Act: -0.0000

Data Index: 165710 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.2991. Min Act: -0.0000

Data Index: 1140983 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.3092. Min Act: -0.0000

Data Index: 540842 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.4615. Min Act: -0.0000

Data Index: 554604 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5852. Min Act: -0.0000

Data Index: 929338 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.2726. Min Act: -0.0000

Data Index: 30138 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.3992. Min Act: -0.0000

Data Index: 1063745 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5485. Min Act: -0.0000

Data Index: 1171068 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 3.7073. Min Range: -3.7073

Max Act: 3.5472. Min Act: -0.0000

Data Index: 1096626 (C4 (Web Text))

Max Activating Token Index: 721