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

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

Neuron 388 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: 3.3510. Min Range: -3.3510

Max Act: 3.3510. Min Act: -0.1700

Data Index: 1615450 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3432. Min Act: -0.1699

Data Index: 1538859 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3347. Min Act: -0.1699

Data Index: 1447083 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3278. Min Act: -0.1700

Data Index: 314118 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1635671 (Python Code)

Max Activating Token Index: 580

Text #5

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3206. Min Act: -0.1699

Data Index: 1601733 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2997. Min Act: -0.1700

Data Index: 621630 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1525407 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3004. Min Act: -0.1699

Data Index: 1582878 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.3007. Min Act: -0.1700

Data Index: 27467 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2870. Min Act: -0.1700

Data Index: 1528973 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2674. Min Act: -0.1699

Data Index: 1581500 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2734. Min Act: -0.1699

Data Index: 1369893 (Python Code)

Max Activating Token Index: 593

Text #13

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2672. Min Act: -0.1700

Data Index: 1590893 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2791. Min Act: -0.1700

Data Index: 522172 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2482. Min Act: -0.1700

Data Index: 1547558 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2599. Min Act: -0.1699

Data Index: 1618223 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2479. Min Act: -0.1700

Data Index: 1636327 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2555. Min Act: -0.1700

Data Index: 1040374 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.3510. Min Range: -3.3510

Max Act: 3.2510. Min Act: -0.1698

Data Index: 1130159 (C4 (Web Text))

Max Activating Token Index: 822