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

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

Neuron 1508 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.8700. Min Act: -0.0001

Data Index: 1105759 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7410. Min Act: -0.0000

Data Index: 156943 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.7303. Min Act: -0.0001

Data Index: 775519 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1597093 (Python Code)

Max Activating Token Index: 708

Text #4

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6254. Min Act: -0.0001

Data Index: 1229427 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6614. Min Act: -0.0001

Data Index: 400844 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6813. Min Act: -0.0001

Data Index: 983581 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6763. Min Act: -0.0001

Data Index: 820714 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6897. Min Act: -0.0001

Data Index: 347780 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6437. Min Act: -0.0001

Data Index: 188767 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5759. Min Act: -0.0001

Data Index: 331284 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6107. Min Act: -0.0001

Data Index: 1495981 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6347. Min Act: -0.0001

Data Index: 262941 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5902. Min Act: -0.0001

Data Index: 604416 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5897. Min Act: -0.0001

Data Index: 1274265 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5838. Min Act: -0.0001

Data Index: 808022 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6338. Min Act: -0.0001

Data Index: 1029024 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1471224 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.5411. Min Act: -0.0001

Data Index: 1474252 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 0.8700. Min Range: -0.8700

Max Act: 0.6062. Min Act: -0.0001

Data Index: 1599514 (Python Code)

Max Activating Token Index: 598