Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 358 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.8419. Min Act: -0.1698

Data Index: 1484908 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.8289. Min Act: -0.1686

Data Index: 1565905 (Python Code)

Max Activating Token Index: 623

Text #2

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3861. Min Act: -0.1700

Data Index: 1592939 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.4095. Min Act: -0.1700

Data Index: 1651167 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.4261. Min Act: -0.1700

Data Index: 1481650 (Python Code)

Max Activating Token Index: 491

Text #5

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.4392. Min Act: -0.1700

Data Index: 1608250 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3293. Min Act: -0.1699

Data Index: 748999 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3325. Min Act: -0.1700

Data Index: 1467270 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3180. Min Act: -0.1700

Data Index: 1515442 (Python Code)

Max Activating Token Index: 807

Text #9

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3496. Min Act: -0.1661

Data Index: 437909 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3499. Min Act: -0.1700

Data Index: 1201602 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.3330. Min Act: -0.1700

Data Index: 451796 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2537. Min Act: -0.1653

Data Index: 1378028 (Python Code)

Max Activating Token Index: 716

Text #13

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2873. Min Act: -0.1699

Data Index: 29570 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2596. Min Act: -0.1700

Data Index: 523659 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2980. Min Act: -0.1700

Data Index: 1493980 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2839. Min Act: -0.1700

Data Index: 1636108 (Python Code)

Max Activating Token Index: 799

Text #17

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2474. Min Act: -0.1700

Data Index: 1433253 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2179. Min Act: -0.1700

Data Index: 1600835 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 4.8419. Min Range: -4.8419

Max Act: 4.2238. Min Act: -0.1699

Data Index: 830602 (C4 (Web Text))

Max Activating Token Index: 991