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

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

Neuron 326 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: 5.6942. Min Range: -5.6942

Max Act: 5.6942. Min Act: -0.1695

Data Index: 1538350 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.6876. Min Act: -0.1700

Data Index: 1565178 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.5026. Min Act: -0.1700

Data Index: 1362038 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4611. Min Act: -0.1700

Data Index: 1559765 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4636. Min Act: -0.1700

Data Index: 1561446 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4341. Min Act: -0.1700

Data Index: 1415968 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4461. Min Act: -0.1700

Data Index: 1361339 (Python Code)

Max Activating Token Index: 952

Text #7

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4303. Min Act: -0.1700

Data Index: 1370566 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4441. Min Act: -0.1700

Data Index: 1371412 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4307. Min Act: -0.1700

Data Index: 1387211 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3996. Min Act: -0.1700

Data Index: 1384873 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4057. Min Act: -0.1700

Data Index: 1443933 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3961. Min Act: -0.1700

Data Index: 1593391 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4234. Min Act: -0.1700

Data Index: 1647543 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.4173. Min Act: -0.1700

Data Index: 1592303 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3697. Min Act: -0.1700

Data Index: 1558709 (Python Code)

Max Activating Token Index: 1021

Text #16

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3811. Min Act: -0.1700

Data Index: 1360208 (Python Code)

Max Activating Token Index: 625

Text #17

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3966. Min Act: -0.1700

Data Index: 1495623 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3398. Min Act: -0.1700

Data Index: 1455935 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 5.6942. Min Range: -5.6942

Max Act: 5.3428. Min Act: -0.1700

Data Index: 1646384 (Python Code)

Max Activating Token Index: 227