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

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

Neuron 2396 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6954. Min Act: -0.0000

Data Index: 133665 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6941. Min Act: -0.0000

Data Index: 289248 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6876. Min Act: -0.0000

Data Index: 60887 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1356383 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1165771 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6218. Min Act: -0.0000

Data Index: 990423 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6299. Min Act: 0.0000

Data Index: 1524353 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6289. Min Act: -0.0000

Data Index: 785581 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6033. Min Act: -0.0000

Data Index: 248662 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5840. Min Act: -0.0000

Data Index: 68819 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5643. Min Act: -0.0000

Data Index: 206987 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1284657 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5665. Min Act: -0.0000

Data Index: 504424 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5857. Min Act: -0.0000

Data Index: 217958 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5664. Min Act: -0.0000

Data Index: 326018 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5451. Min Act: -0.0000

Data Index: 19642 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1432445 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1069245 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5528. Min Act: -0.0000

Data Index: 77565 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5382. Min Act: -0.0000

Data Index: 155609 (C4 (Web Text))

Max Activating Token Index: 223