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

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

Neuron 2938 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.6504. Min Act: -0.0003

Data Index: 824048 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.4795. Min Act: -0.0002

Data Index: 99358 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.4335. Min Act: -0.0002

Data Index: 1262664 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.4373. Min Act: -0.0002

Data Index: 967583 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3997. Min Act: -0.0002

Data Index: 979522 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3656. Min Act: -0.0002

Data Index: 1112216 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3800. Min Act: -0.0002

Data Index: 942569 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3669. Min Act: -0.0002

Data Index: 2753 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3601. Min Act: -0.0002

Data Index: 895327 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3212. Min Act: -0.0003

Data Index: 903099 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3447. Min Act: -0.0002

Data Index: 368278 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.3032. Min Act: -0.0002

Data Index: 1141227 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2953. Min Act: -0.0002

Data Index: 571689 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2774. Min Act: -0.0002

Data Index: 415309 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2776. Min Act: -0.0002

Data Index: 934215 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2795. Min Act: -0.0002

Data Index: 1291085 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2295. Min Act: -0.0003

Data Index: 1339500 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2556. Min Act: -0.0002

Data Index: 1222424 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2341. Min Act: -0.0002

Data Index: 1169147 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.6504. Min Range: -1.6504

Max Act: 1.2437. Min Act: -0.0003

Data Index: 1244748 (C4 (Web Text))

Max Activating Token Index: 212