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

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

Neuron 1395 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: 3.2384. Min Range: -3.2384

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1560049 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.2210. Min Act: -0.1700

Data Index: 1645428 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1893. Min Act: -0.1700

Data Index: 1609873 (Python Code)

Max Activating Token Index: 865

Text #3

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1791. Min Act: -0.1700

Data Index: 1606492 (Python Code)

Max Activating Token Index: 737

Text #4

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1674. Min Act: -0.1700

Data Index: 138355 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1328. Min Act: -0.1700

Data Index: 495120 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1310. Min Act: -0.1700

Data Index: 1547307 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1333. Min Act: -0.1700

Data Index: 1284044 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1622. Min Act: -0.1700

Data Index: 1587467 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1566793 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1337528 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.1230. Min Act: -0.1700

Data Index: 1218708 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0844. Min Act: -0.1700

Data Index: 917429 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0670. Min Act: -0.1700

Data Index: 807994 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0603. Min Act: -0.1700

Data Index: 965632 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0643. Min Act: -0.1700

Data Index: 887168 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0377. Min Act: -0.1700

Data Index: 1533360 (Python Code)

Max Activating Token Index: 945

Text #17

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0552. Min Act: -0.1700

Data Index: 1644366 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0724. Min Act: -0.1700

Data Index: 1270063 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 3.2384. Min Range: -3.2384

Max Act: 3.0583. Min Act: -0.1700

Data Index: 1183093 (C4 (Web Text))

Max Activating Token Index: 56