Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3249 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3520. Min Range: -2.3520

Max Act: 2.3520. Min Act: -0.0000

Data Index: 736722 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 2.3520. Min Range: -2.3520

Max Act: 2.2977. Min Act: -0.0000

Data Index: 950820 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 2.3520. Min Range: -2.3520

Max Act: 2.2229. Min Act: -0.0000

Data Index: 390449 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1181060 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 2.3520. Min Range: -2.3520

Max Act: 2.0309. Min Act: -0.0000

Data Index: 438530 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.9097. Min Act: -0.0000

Data Index: 987203 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.8972. Min Act: -0.0000

Data Index: 178263 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.9162. Min Act: -0.0000

Data Index: 805678 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.7409. Min Act: -0.0000

Data Index: 700884 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.9019. Min Act: -0.0000

Data Index: 546439 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.8144. Min Act: -0.0000

Data Index: 854072 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.8139. Min Act: -0.0000

Data Index: 207474 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.7823. Min Act: -0.0000

Data Index: 828875 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.8045. Min Act: -0.0000

Data Index: 1268615 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1055429 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.7001. Min Act: -0.0000

Data Index: 468928 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.6767. Min Act: -0.0000

Data Index: 1106754 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.8142. Min Act: -0.0000

Data Index: 485793 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1112400 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 2.3520. Min Range: -2.3520

Max Act: 1.6953. Min Act: -0.0000

Data Index: 311957 (C4 (Web Text))

Max Activating Token Index: 418