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

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

Neuron 964 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: 1.4265. Min Range: -1.4265

Max Act: 1.4265. Min Act: -0.0001

Data Index: 445354 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.4060. Min Act: -0.0001

Data Index: 396805 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.4099. Min Act: -0.0001

Data Index: 1221171 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3462. Min Act: -0.0001

Data Index: 375315 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3971. Min Act: -0.0001

Data Index: 730356 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3920. Min Act: -0.0001

Data Index: 696434 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3923. Min Act: -0.0001

Data Index: 997047 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3360. Min Act: -0.0001

Data Index: 92090 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3332. Min Act: -0.0001

Data Index: 1259016 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.2921. Min Act: -0.0001

Data Index: 532975 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3922. Min Act: -0.0001

Data Index: 21359 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3160. Min Act: -0.0001

Data Index: 637753 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3068. Min Act: -0.0001

Data Index: 980221 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.2643. Min Act: -0.0001

Data Index: 1201488 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.2975. Min Act: -0.0001

Data Index: 850690 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3288. Min Act: -0.0001

Data Index: 388483 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.2966. Min Act: -0.0001

Data Index: 219883 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3764. Min Act: -0.0001

Data Index: 96523 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3320. Min Act: -0.0001

Data Index: 377058 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.4265. Min Range: -1.4265

Max Act: 1.3375. Min Act: -0.0001

Data Index: 1102465 (C4 (Web Text))

Max Activating Token Index: 201