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

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

Neuron 1537 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: 2.2685. Min Range: -2.2685

Max Act: 2.1057. Min Act: -0.0000

Data Index: 1196578 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 2.2685. Min Range: -2.2685

Max Act: 2.1334. Min Act: -0.0000

Data Index: 229643 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 2.2685. Min Range: -2.2685

Max Act: 2.2685. Min Act: -0.0000

Data Index: 1120559 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 2.2685. Min Range: -2.2685

Max Act: 2.0263. Min Act: -0.0000

Data Index: 1196454 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 2.2685. Min Range: -2.2685

Max Act: 2.1163. Min Act: -0.0000

Data Index: 769068 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.9663. Min Act: -0.0000

Data Index: 1175695 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.8596. Min Act: -0.0000

Data Index: 19167 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.8336. Min Act: -0.0000

Data Index: 534332 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.7270. Min Act: -0.0000

Data Index: 393710 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.6491. Min Act: -0.0000

Data Index: 353650 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1312283 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1134299 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.4367. Min Act: -0.0000

Data Index: 790614 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.4562. Min Act: -0.0000

Data Index: 949545 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.3667. Min Act: -0.0000

Data Index: 309205 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1205052 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.3225. Min Act: -0.0000

Data Index: 672624 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.4070. Min Act: -0.0000

Data Index: 37378 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.3525. Min Act: -0.0000

Data Index: 432431 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 2.2685. Min Range: -2.2685

Max Act: 1.2464. Min Act: -0.0000

Data Index: 484500 (C4 (Web Text))

Max Activating Token Index: 213