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

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

Neuron 1459 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: 3.5208. Min Range: -3.5208

Max Act: 3.4887. Min Act: -0.1700

Data Index: 1562048 (Python Code)

Max Activating Token Index: 505

Text #1

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1435800 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4339. Min Act: -0.1700

Data Index: 1486905 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4661. Min Act: -0.1700

Data Index: 1654917 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1436772 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3815. Min Act: -0.1700

Data Index: 1533707 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3633. Min Act: -0.1700

Data Index: 1476366 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4209. Min Act: -0.1700

Data Index: 1454798 (Python Code)

Max Activating Token Index: 145

Text #8

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1543609 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4407. Min Act: -0.1700

Data Index: 1386959 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1624163 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3655. Min Act: -0.1700

Data Index: 1569916 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3428. Min Act: -0.1700

Data Index: 1596681 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3650. Min Act: -0.1700

Data Index: 1502381 (Python Code)

Max Activating Token Index: 465

Text #14

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4006. Min Act: -0.1700

Data Index: 1460332 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4236. Min Act: -0.1700

Data Index: 1395669 (Python Code)

Max Activating Token Index: 776

Text #16

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3605. Min Act: -0.1700

Data Index: 1415895 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3503. Min Act: -0.1700

Data Index: 1380199 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3807. Min Act: -0.1700

Data Index: 1475073 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3414. Min Act: -0.1700

Data Index: 1632803 (Python Code)

Max Activating Token Index: 715