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

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

Neuron 1716 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3265. Min Act: -0.0000

Data Index: 954008 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3072. Min Act: -0.0001

Data Index: 1582241 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3337. Min Act: -0.0001

Data Index: 8148 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2987. Min Act: -0.0001

Data Index: 493070 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2923. Min Act: -0.0000

Data Index: 9452 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2944. Min Act: -0.0001

Data Index: 935913 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2900. Min Act: -0.0001

Data Index: 107612 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2938. Min Act: -0.0001

Data Index: 468831 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1258887 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1150779 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1106735 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2914. Min Act: -0.0001

Data Index: 614005 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2977. Min Act: -0.0001

Data Index: 986948 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2788. Min Act: -0.0001

Data Index: 1116158 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2760. Min Act: -0.0000

Data Index: 156080 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1437191 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2751. Min Act: -0.0001

Data Index: 822077 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2824. Min Act: -0.0001

Data Index: 576771 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1422918 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1573044 (Python Code)

Max Activating Token Index: 344