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

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

Neuron 5931 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7782. Min Range: -5.7782

Max Act: 5.7782. Min Act: -0.0000

Data Index: 326714 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.3791. Min Act: -0.0000

Data Index: 619259 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.3028. Min Act: -0.0000

Data Index: 1043195 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.4496. Min Act: -0.0000

Data Index: 579641 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.1625. Min Act: -0.0000

Data Index: 197322 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.4941. Min Act: -0.0000

Data Index: 384497 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.2140. Min Act: -0.0000

Data Index: 595362 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.3560. Min Act: -0.0000

Data Index: 313167 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.2340. Min Act: -0.0000

Data Index: 1214969 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.8831. Min Act: -0.0000

Data Index: 890904 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 5.7782. Min Range: -5.7782

Max Act: 4.1505. Min Act: -0.0000

Data Index: 567991 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.9398. Min Act: -0.0000

Data Index: 1105030 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.7048. Min Act: -0.0000

Data Index: 1163244 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.8063. Min Act: -0.0000

Data Index: 142477 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.7379. Min Act: -0.0000

Data Index: 1091385 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.8749. Min Act: -0.0000

Data Index: 44517 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.6987. Min Act: -0.0000

Data Index: 730962 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.4312. Min Act: -0.0000

Data Index: 1020384 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.1180. Min Act: -0.0000

Data Index: 1289541 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 5.7782. Min Range: -5.7782

Max Act: 3.3951. Min Act: -0.0000

Data Index: 1292479 (C4 (Web Text))

Max Activating Token Index: 337