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

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

Neuron 1068 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1352058 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4619. Min Act: -0.0000

Data Index: 952455 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.5003. Min Act: -0.0000

Data Index: 68612 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4803. Min Act: -0.0000

Data Index: 64060 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1036353 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4276. Min Act: -0.0000

Data Index: 952268 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4600. Min Act: -0.0000

Data Index: 540740 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4040. Min Act: -0.0000

Data Index: 450354 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1214090 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4350. Min Act: -0.0000

Data Index: 863358 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4376. Min Act: -0.0000

Data Index: 713263 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3985. Min Act: -0.0000

Data Index: 935586 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3790. Min Act: -0.0000

Data Index: 484275 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1201674 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4139. Min Act: -0.0000

Data Index: 524807 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1122687 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4021. Min Act: -0.0000

Data Index: 244245 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3231. Min Act: -0.0000

Data Index: 173621 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3832. Min Act: -0.0000

Data Index: 355015 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1285853 (C4 (Web Text))

Max Activating Token Index: 376