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

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

Neuron 1862 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: 3.5486. Min Range: -3.5486

Max Act: 3.5486. Min Act: -0.1700

Data Index: 1434938 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.5308. Min Act: -0.1700

Data Index: 1378135 (Python Code)

Max Activating Token Index: 387

Text #2

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.4890. Min Act: -0.1700

Data Index: 1409175 (Python Code)

Max Activating Token Index: 728

Text #3

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1546545 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3771. Min Act: -0.1700

Data Index: 610993 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3773. Min Act: -0.1700

Data Index: 1316793 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3949. Min Act: -0.1700

Data Index: 165661 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1629949 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3491. Min Act: -0.1700

Data Index: 1076953 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3935. Min Act: -0.1700

Data Index: 1137013 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3479. Min Act: -0.1700

Data Index: 570634 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3325. Min Act: -0.1700

Data Index: 674522 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3382. Min Act: -0.1700

Data Index: 143872 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3515. Min Act: -0.1700

Data Index: 380575 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.2924. Min Act: -0.1700

Data Index: 1121626 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3206. Min Act: -0.1700

Data Index: 1421803 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3274. Min Act: -0.1700

Data Index: 1439389 (Python Code)

Max Activating Token Index: 969

Text #17

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3239. Min Act: -0.1700

Data Index: 842219 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.2847. Min Act: -0.1700

Data Index: 403993 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 3.5486. Min Range: -3.5486

Max Act: 3.3305. Min Act: -0.1700

Data Index: 406404 (C4 (Web Text))

Max Activating Token Index: 664