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

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

Neuron 1944 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: 1.7366. Min Range: -1.7366

Max Act: 1.7366. Min Act: -0.0001

Data Index: 1284885 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.5042. Min Act: -0.0001

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.4078. Min Act: -0.0001

Data Index: 91078 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.4792. Min Act: -0.0001

Data Index: 555489 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.4864. Min Act: -0.0001

Data Index: 679050 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.3301. Min Act: -0.0001

Data Index: 693705 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.3658. Min Act: -0.0001

Data Index: 1333816 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.4051. Min Act: -0.0001

Data Index: 394241 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.2417. Min Act: -0.0001

Data Index: 686898 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.2047. Min Act: -0.0001

Data Index: 684354 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.1866. Min Act: -0.0001

Data Index: 589445 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.1631. Min Act: -0.0001

Data Index: 1013415 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.1476. Min Act: -0.0001

Data Index: 1316708 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.1369. Min Act: -0.0001

Data Index: 1021328 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.1016. Min Act: -0.0001

Data Index: 276725 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.0136. Min Act: -0.0001

Data Index: 1316537 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.1012. Min Act: -0.0001

Data Index: 1065113 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.0454. Min Act: -0.0001

Data Index: 290065 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.0058. Min Act: -0.0001

Data Index: 327655 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.7366. Min Range: -1.7366

Max Act: 1.0377. Min Act: -0.0001

Data Index: 717151 (C4 (Web Text))

Max Activating Token Index: 546