Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5169 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1311943 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1430. Min Act: -0.0001

Data Index: 563179 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8418. Min Act: -0.0001

Data Index: 421464 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1157398 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.1464. Min Act: -0.0001

Data Index: 1083385 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9336. Min Act: -0.0001

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0223. Min Act: -0.0001

Data Index: 612531 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9779. Min Act: -0.0001

Data Index: 406333 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9658. Min Act: -0.0001

Data Index: 106591 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9049. Min Act: -0.0001

Data Index: 1315282 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8696. Min Act: -0.0001

Data Index: 194221 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.1464. Min Range: -1.1464

Max Act: 1.0390. Min Act: -0.0001

Data Index: 1275689 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9516. Min Act: -0.0001

Data Index: 654263 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8870. Min Act: -0.0001

Data Index: 804472 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9758. Min Act: -0.0001

Data Index: 91641 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9373. Min Act: -0.0001

Data Index: 1190588 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9829. Min Act: -0.0001

Data Index: 220957 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.8804. Min Act: -0.0001

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.9450. Min Act: -0.0001

Data Index: 47300 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.1464. Min Range: -1.1464

Max Act: 0.7364. Min Act: -0.0001

Data Index: 1173111 (C4 (Web Text))

Max Activating Token Index: 321