Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2296 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.3384. Min Act: -0.0001

Data Index: 839721 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.2717. Min Act: -0.0001

Data Index: 1436597 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.3233. Min Act: -0.0001

Data Index: 509568 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.1447. Min Act: -0.0001

Data Index: 1163575 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.1277. Min Act: -0.0001

Data Index: 1177330 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0500. Min Act: -0.0001

Data Index: 1526665 (Python Code)

Max Activating Token Index: 311

Text #6

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0867. Min Act: -0.0001

Data Index: 1447073 (Python Code)

Max Activating Token Index: 465

Text #7

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0537. Min Act: -0.0001

Data Index: 1393596 (Python Code)

Max Activating Token Index: 467

Text #8

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0363. Min Act: -0.0001

Data Index: 1068556 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0337. Min Act: -0.0001

Data Index: 29110 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0681. Min Act: -0.0001

Data Index: 1501612 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9982. Min Act: -0.0001

Data Index: 1002384 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0101. Min Act: -0.0001

Data Index: 1448061 (Python Code)

Max Activating Token Index: 743

Text #13

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9737. Min Act: -0.0001

Data Index: 1432325 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9784. Min Act: -0.0001

Data Index: 1444992 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9407. Min Act: -0.0001

Data Index: 1522065 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9930. Min Act: -0.0001

Data Index: 1620906 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 1.3384. Min Range: -1.3384

Max Act: 1.0168. Min Act: -0.0001

Data Index: 1370074 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9502. Min Act: -0.0001

Data Index: 1539773 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 1.3384. Min Range: -1.3384

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1638626 (Python Code)

Max Activating Token Index: 206