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

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

Neuron 2792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.5203. Min Act: -0.0001

Data Index: 133286 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4116. Min Act: -0.0001

Data Index: 983190 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3785. Min Act: -0.0001

Data Index: 1004670 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3178. Min Act: -0.0001

Data Index: 1138291 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.4723. Min Act: -0.0001

Data Index: 970098 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3475. Min Act: -0.0001

Data Index: 1161569 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3559. Min Act: -0.0001

Data Index: 886263 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3797. Min Act: -0.0001

Data Index: 98213 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3395. Min Act: -0.0001

Data Index: 480412 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3335. Min Act: -0.0001

Data Index: 1269600 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3077. Min Act: -0.0001

Data Index: 831071 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.2931. Min Act: -0.0001

Data Index: 459367 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3468. Min Act: -0.0001

Data Index: 1200085 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3121. Min Act: -0.0001

Data Index: 746301 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3092. Min Act: -0.0001

Data Index: 41026 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3522. Min Act: -0.0001

Data Index: 1310303 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3413. Min Act: -0.0001

Data Index: 542238 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3312. Min Act: -0.0001

Data Index: 512863 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3048. Min Act: -0.0001

Data Index: 315035 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.5203. Min Range: -0.5203

Max Act: 0.3254. Min Act: -0.0001

Data Index: 1359155 (C4 (Web Text))

Max Activating Token Index: 668