Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3553 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.5059. Min Act: -0.0001

Data Index: 483813 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4942. Min Act: -0.0001

Data Index: 597894 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.5081. Min Act: -0.0001

Data Index: 1147066 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4951. Min Act: -0.0001

Data Index: 479054 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1327559 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.5103. Min Act: -0.0001

Data Index: 241454 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4914. Min Act: -0.0001

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4680. Min Act: -0.0001

Data Index: 1091840 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4845. Min Act: -0.0001

Data Index: 830351 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4623. Min Act: -0.0001

Data Index: 205367 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4969. Min Act: -0.0001

Data Index: 436314 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1303876 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4937. Min Act: -0.0001

Data Index: 754799 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4785. Min Act: -0.0001

Data Index: 176789 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4696. Min Act: -0.0001

Data Index: 312506 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1215114 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4687. Min Act: -0.0001

Data Index: 97610 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4521. Min Act: -0.0001

Data Index: 394803 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1101519 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4769. Min Act: -0.0001

Data Index: 90653 (C4 (Web Text))

Max Activating Token Index: 801