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

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

Neuron 1824 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: 3.8147. Min Range: -3.8147

Max Act: 3.8147. Min Act: -0.1700

Data Index: 1644662 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.7428. Min Act: -0.1700

Data Index: 527527 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.7507. Min Act: -0.1700

Data Index: 1507691 (Python Code)

Max Activating Token Index: 507

Text #3

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.7672. Min Act: -0.1700

Data Index: 1456850 (Python Code)

Max Activating Token Index: 926

Text #4

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.7363. Min Act: -0.1700

Data Index: 1480870 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.7319. Min Act: -0.1700

Data Index: 1614989 (Python Code)

Max Activating Token Index: 831

Text #6

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.6777. Min Act: -0.1700

Data Index: 357306 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.6077. Min Act: -0.1700

Data Index: 1649302 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5952. Min Act: -0.1700

Data Index: 589151 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5968. Min Act: -0.1700

Data Index: 28892 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5931. Min Act: -0.1700

Data Index: 1398519 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5665. Min Act: -0.1700

Data Index: 1635035 (Python Code)

Max Activating Token Index: 919

Text #12

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5351. Min Act: -0.1700

Data Index: 1423900 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5421. Min Act: -0.1700

Data Index: 1019325 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5501. Min Act: -0.1700

Data Index: 773622 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5453. Min Act: -0.1700

Data Index: 1625813 (Python Code)

Max Activating Token Index: 443

Text #16

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5403. Min Act: -0.1700

Data Index: 1461891 (Python Code)

Max Activating Token Index: 469

Text #17

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5217. Min Act: -0.1700

Data Index: 1421804 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.5027. Min Act: -0.1700

Data Index: 1634993 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 3.8147. Min Range: -3.8147

Max Act: 3.4944. Min Act: -0.1700

Data Index: 1054720 (C4 (Web Text))

Max Activating Token Index: 984