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

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

Neuron 1523 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: 4.2298. Min Range: -4.2298

Max Act: 4.1737. Min Act: -0.1700

Data Index: 797717 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.2298. Min Act: -0.1700

Data Index: 28305 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.1365. Min Act: -0.1700

Data Index: 432910 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0759. Min Act: -0.1700

Data Index: 853833 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0753. Min Act: -0.1700

Data Index: 1466562 (Python Code)

Max Activating Token Index: 952

Text #5

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0366. Min Act: -0.1700

Data Index: 514226 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0595. Min Act: -0.1700

Data Index: 289567 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0429. Min Act: -0.1700

Data Index: 250748 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0394. Min Act: -0.1700

Data Index: 268689 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9452. Min Act: -0.1700

Data Index: 620096 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0202. Min Act: -0.1700

Data Index: 595043 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 4.2298. Min Range: -4.2298

Max Act: 4.0070. Min Act: -0.1700

Data Index: 784137 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9602. Min Act: -0.1700

Data Index: 1361283 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9410. Min Act: -0.1700

Data Index: 973539 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9723. Min Act: -0.1700

Data Index: 645212 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9584. Min Act: -0.1700

Data Index: 835556 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9749. Min Act: -0.1700

Data Index: 998637 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9411. Min Act: -0.1700

Data Index: 975325 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9444. Min Act: -0.1700

Data Index: 1261615 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 4.2298. Min Range: -4.2298

Max Act: 3.9392. Min Act: -0.1700

Data Index: 1116148 (C4 (Web Text))

Max Activating Token Index: 783