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

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

Neuron 1609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.7794. Min Act: -0.0001

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 3.1013. Min Range: -3.1013

Max Act: 3.1013. Min Act: -0.0001

Data Index: 267181 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.9187. Min Act: -0.0001

Data Index: 1012668 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.8157. Min Act: -0.0001

Data Index: 542454 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.5652. Min Act: -0.0001

Data Index: 1236375 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.2920. Min Act: -0.0001

Data Index: 164884 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.4205. Min Act: -0.0001

Data Index: 623024 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.4577. Min Act: -0.0001

Data Index: 658259 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.3076. Min Act: -0.0001

Data Index: 1580453 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.4308. Min Act: -0.0001

Data Index: 1043794 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.1818. Min Act: -0.0001

Data Index: 917653 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.2911. Min Act: -0.0001

Data Index: 497591 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.4695. Min Act: -0.0001

Data Index: 264520 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.3267. Min Act: -0.0001

Data Index: 1620477 (Python Code)

Max Activating Token Index: 200

Text #14

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.3262. Min Act: -0.0001

Data Index: 250496 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.4342. Min Act: -0.0001

Data Index: 262008 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.2079. Min Act: -0.0001

Data Index: 1294313 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.3156. Min Act: -0.0001

Data Index: 1379202 (Python Code)

Max Activating Token Index: 460

Text #18

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.3169. Min Act: -0.0001

Data Index: 1175404 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 3.1013. Min Range: -3.1013

Max Act: 2.3008. Min Act: -0.0001

Data Index: 1638550 (Python Code)

Max Activating Token Index: 923