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

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

Neuron 309 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: 3.9698. Min Range: -3.9698

Max Act: 3.9698. Min Act: -0.1700

Data Index: 1432031 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.7540. Min Act: -0.1699

Data Index: 1633629 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.7594. Min Act: -0.1700

Data Index: 1435882 (Python Code)

Max Activating Token Index: 84

Text #3

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.7347. Min Act: -0.1700

Data Index: 1447565 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.7070. Min Act: -0.1700

Data Index: 1590211 (Python Code)

Max Activating Token Index: 966

Text #5

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.6161. Min Act: -0.1700

Data Index: 1608545 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5970. Min Act: -0.1699

Data Index: 1448433 (Python Code)

Max Activating Token Index: 587

Text #7

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.6078. Min Act: -0.1700

Data Index: 1614770 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5874. Min Act: -0.1690

Data Index: 1578213 (Python Code)

Max Activating Token Index: 978

Text #9

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5766. Min Act: -0.1700

Data Index: 1608837 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5662. Min Act: -0.1700

Data Index: 1608142 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5866. Min Act: -0.1700

Data Index: 1430323 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5837. Min Act: -0.1700

Data Index: 1641514 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5763. Min Act: -0.1699

Data Index: 1387125 (Python Code)

Max Activating Token Index: 617

Text #14

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5694. Min Act: -0.1700

Data Index: 1519605 (Python Code)

Max Activating Token Index: 652

Text #15

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5192. Min Act: -0.1699

Data Index: 1610516 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5466. Min Act: -0.1700

Data Index: 1482405 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5642. Min Act: -0.1688

Data Index: 1441804 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5308. Min Act: -0.1700

Data Index: 1364204 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 3.9698. Min Range: -3.9698

Max Act: 3.5426. Min Act: -0.1700

Data Index: 1536380 (Python Code)

Max Activating Token Index: 857