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

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

Neuron 633 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: 3.5003. Min Range: -3.5003

Max Act: 3.4811. Min Act: -0.1700

Data Index: 1436453 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.5003. Min Act: -0.1700

Data Index: 1472549 (Python Code)

Max Activating Token Index: 910

Text #2

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1498911 (Python Code)

Max Activating Token Index: 600

Text #3

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4606. Min Act: -0.1699

Data Index: 1441293 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4446. Min Act: -0.1700

Data Index: 1381441 (Python Code)

Max Activating Token Index: 932

Text #5

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4356. Min Act: -0.1689

Data Index: 1635280 (Python Code)

Max Activating Token Index: 958

Text #6

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4234. Min Act: -0.1700

Data Index: 1369280 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4294. Min Act: -0.1699

Data Index: 1511064 (Python Code)

Max Activating Token Index: 600

Text #8

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4169. Min Act: -0.1699

Data Index: 1537517 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4185. Min Act: -0.1700

Data Index: 477346 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4124. Min Act: -0.1700

Data Index: 1511946 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1472708 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.4088. Min Act: -0.1700

Data Index: 1057245 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3874. Min Act: -0.1700

Data Index: 1118832 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3615. Min Act: -0.1678

Data Index: 1468021 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3606. Min Act: -0.1700

Data Index: 1564542 (Python Code)

Max Activating Token Index: 569

Text #16

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3616. Min Act: -0.1700

Data Index: 1477594 (Python Code)

Max Activating Token Index: 439

Text #17

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3589. Min Act: -0.1671

Data Index: 1383091 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3494. Min Act: -0.1699

Data Index: 1546935 (Python Code)

Max Activating Token Index: 416

Text #19

Max Range: 3.5003. Min Range: -3.5003

Max Act: 3.3330. Min Act: -0.1700

Data Index: 1500702 (Python Code)

Max Activating Token Index: 980