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

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

Neuron 1111 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: 3.6487. Min Range: -3.6487

Max Act: 3.6487. Min Act: -0.1700

Data Index: 1365361 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.6438. Min Act: -0.1700

Data Index: 1410248 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.5533. Min Act: -0.1700

Data Index: 1581925 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4727. Min Act: -0.1700

Data Index: 1533013 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4399. Min Act: -0.1700

Data Index: 1582834 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4200. Min Act: -0.1700

Data Index: 1544050 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.4258. Min Act: -0.1700

Data Index: 1651668 (Python Code)

Max Activating Token Index: 523

Text #7

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3937. Min Act: -0.1700

Data Index: 1542819 (Python Code)

Max Activating Token Index: 292

Text #8

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3868. Min Act: -0.1700

Data Index: 900434 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3620. Min Act: -0.1700

Data Index: 1649753 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3762. Min Act: -0.1680

Data Index: 1647443 (Python Code)

Max Activating Token Index: 758

Text #11

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3442. Min Act: -0.1698

Data Index: 1567724 (Python Code)

Max Activating Token Index: 614

Text #12

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3445. Min Act: -0.1700

Data Index: 1412944 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3414. Min Act: -0.1700

Data Index: 1449678 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3417. Min Act: -0.1700

Data Index: 1590886 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1597629 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3229. Min Act: -0.1700

Data Index: 1497015 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3346. Min Act: -0.1700

Data Index: 1557166 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1386818 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 3.6487. Min Range: -3.6487

Max Act: 3.3255. Min Act: -0.1699

Data Index: 1596597 (Python Code)

Max Activating Token Index: 466