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

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

Neuron 161 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: 4.1225. Min Range: -4.1225

Max Act: 4.1225. Min Act: -0.1638

Data Index: 1572976 (Python Code)

Max Activating Token Index: 921

Text #1

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.9386. Min Act: -0.1698

Data Index: 1558625 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.8631. Min Act: -0.1651

Data Index: 1634176 (Python Code)

Max Activating Token Index: 541

Text #3

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.8367. Min Act: -0.1695

Data Index: 1600033 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.8374. Min Act: -0.1668

Data Index: 1373496 (Python Code)

Max Activating Token Index: 372

Text #5

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.8084. Min Act: -0.1698

Data Index: 1537888 (Python Code)

Max Activating Token Index: 453

Text #6

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1113251 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7323. Min Act: -0.1700

Data Index: 1506743 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1497771 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7413. Min Act: -0.1700

Data Index: 1393711 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7365. Min Act: -0.1638

Data Index: 1497353 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7059. Min Act: -0.1700

Data Index: 986734 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.7014. Min Act: -0.1698

Data Index: 1614056 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6774. Min Act: -0.1697

Data Index: 1556353 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6798. Min Act: -0.1671

Data Index: 1651543 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6484. Min Act: -0.1638

Data Index: 1487071 (Python Code)

Max Activating Token Index: 810

Text #16

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6609. Min Act: -0.1692

Data Index: 1537718 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6661. Min Act: -0.1699

Data Index: 1466085 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6479. Min Act: -0.1700

Data Index: 1391453 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 4.1225. Min Range: -4.1225

Max Act: 3.6467. Min Act: -0.1700

Data Index: 1371169 (Python Code)

Max Activating Token Index: 213