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

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

Neuron 2617 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: 1.1030. Min Range: -1.1030

Max Act: 1.0431. Min Act: -0.0000

Data Index: 73664 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1165611 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.1030. Min Act: -0.0000

Data Index: 527310 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0490. Min Act: -0.0000

Data Index: 673397 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1050263 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.5712. Min Act: -0.0000

Data Index: 226755 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.5035. Min Act: -0.0000

Data Index: 530180 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4952. Min Act: -0.0000

Data Index: 906744 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4976. Min Act: -0.0000

Data Index: 341041 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1126555 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4763. Min Act: -0.0000

Data Index: 817412 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1644242 (Python Code)

Max Activating Token Index: 316

Text #12

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4562. Min Act: -0.0000

Data Index: 331384 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1312005 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4307. Min Act: -0.0000

Data Index: 47739 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4277. Min Act: 0.0000

Data Index: 135385 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4337. Min Act: 0.0000

Data Index: 707167 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4367. Min Act: -0.0000

Data Index: 565302 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1115925 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1247487 (C4 (Web Text))

Max Activating Token Index: 786