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

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

Neuron 4470 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.9050. Min Act: -0.0000

Data Index: 667209 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.8106. Min Act: -0.0000

Data Index: 1011375 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.8033. Min Act: -0.0000

Data Index: 457367 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.7762. Min Act: -0.0000

Data Index: 820580 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.6955. Min Act: -0.0000

Data Index: 245062 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.6050. Min Act: -0.0000

Data Index: 190768 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1104218 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.6680. Min Act: -0.0000

Data Index: 493180 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.6547. Min Act: -0.0000

Data Index: 1142859 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.6587. Min Act: -0.0000

Data Index: 465556 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.5578. Min Act: -0.0000

Data Index: 99715 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1332659 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.5132. Min Act: -0.0000

Data Index: 422269 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1628377 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.4775. Min Act: -0.0000

Data Index: 404236 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1409954 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.4789. Min Act: -0.0000

Data Index: 839357 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.3311. Min Act: -0.0000

Data Index: 1061595 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.3671. Min Act: -0.0000

Data Index: 243421 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.9050. Min Range: -1.9050

Max Act: 1.4039. Min Act: -0.0000

Data Index: 625032 (C4 (Web Text))

Max Activating Token Index: 951