Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1528 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1246144 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3665. Min Act: -0.0001

Data Index: 599120 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1321492 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3643. Min Act: -0.0001

Data Index: 245335 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3245. Min Act: -0.0000

Data Index: 669443 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1080004 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3289. Min Act: -0.0001

Data Index: 525767 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3119. Min Act: -0.0001

Data Index: 130958 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3145. Min Act: -0.0001

Data Index: 1133335 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3219. Min Act: -0.0001

Data Index: 609676 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2996. Min Act: -0.0001

Data Index: 505764 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3062. Min Act: -0.0000

Data Index: 707372 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3031. Min Act: -0.0001

Data Index: 1124580 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2993. Min Act: -0.0001

Data Index: 279800 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2927. Min Act: -0.0001

Data Index: 1013882 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3023. Min Act: -0.0001

Data Index: 1026256 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2954. Min Act: -0.0001

Data Index: 955244 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2906. Min Act: -0.0001

Data Index: 311870 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3151. Min Act: -0.0001

Data Index: 246870 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2988. Min Act: -0.0001

Data Index: 171365 (C4 (Web Text))

Max Activating Token Index: 450