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

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

Neuron 4472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0324. Min Range: -1.0324

Max Act: 1.0324. Min Act: -0.0000

Data Index: 118115 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8838. Min Act: -0.0000

Data Index: 338218 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8411. Min Act: -0.0000

Data Index: 127530 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8840. Min Act: -0.0000

Data Index: 910654 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8041. Min Act: -0.0000

Data Index: 398548 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8001. Min Act: -0.0000

Data Index: 561676 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7345. Min Act: -0.0000

Data Index: 15514 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.8264. Min Act: -0.0001

Data Index: 581948 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7295. Min Act: -0.0000

Data Index: 254342 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7559. Min Act: -0.0001

Data Index: 649188 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1343388 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7098. Min Act: -0.0000

Data Index: 919302 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7011. Min Act: -0.0000

Data Index: 497870 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7100. Min Act: -0.0001

Data Index: 141813 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1056043 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7259. Min Act: -0.0000

Data Index: 66886 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.7081. Min Act: -0.0000

Data Index: 696951 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1306181 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.6962. Min Act: -0.0000

Data Index: 923758 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 1.0324. Min Range: -1.0324

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1048149 (C4 (Web Text))

Max Activating Token Index: 901