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

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

Neuron 354 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: 3.9710. Min Range: -3.9710

Max Act: 3.9710. Min Act: -0.1700

Data Index: 1558778 (Python Code)

Max Activating Token Index: 1009

Text #1

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.9517. Min Act: -0.1700

Data Index: 727828 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8972. Min Act: -0.1700

Data Index: 1645892 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8943. Min Act: -0.1700

Data Index: 1458409 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8329. Min Act: -0.1700

Data Index: 178580 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8383. Min Act: -0.1700

Data Index: 1645985 (Python Code)

Max Activating Token Index: 670

Text #6

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8108. Min Act: -0.1700

Data Index: 1350459 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7974. Min Act: -0.1700

Data Index: 647178 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8006. Min Act: -0.1700

Data Index: 200322 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7861. Min Act: -0.1700

Data Index: 729329 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7994. Min Act: -0.1700

Data Index: 1551041 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7740. Min Act: -0.1700

Data Index: 1440199 (Python Code)

Max Activating Token Index: 580

Text #12

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7773. Min Act: -0.1700

Data Index: 1515128 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7735. Min Act: -0.1700

Data Index: 1653342 (Python Code)

Max Activating Token Index: 606

Text #14

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7671. Min Act: -0.1700

Data Index: 50042 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7948. Min Act: -0.1700

Data Index: 1482945 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7762. Min Act: -0.1700

Data Index: 1457635 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7571. Min Act: -0.1700

Data Index: 622570 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.8046. Min Act: -0.1700

Data Index: 1422741 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 3.9710. Min Range: -3.9710

Max Act: 3.7595. Min Act: -0.1700

Data Index: 1440517 (Python Code)

Max Activating Token Index: 698