Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1528 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.2077. Min Act: -0.1700

Data Index: 230968 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.1762. Min Act: -0.1700

Data Index: 1427061 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.1762. Min Act: -0.1700

Data Index: 107255 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1392469 (Python Code)

Max Activating Token Index: 270

Text #4

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.1290. Min Act: -0.1700

Data Index: 314037 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0975. Min Act: -0.1700

Data Index: 1295887 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0343. Min Act: -0.1700

Data Index: 957881 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0343. Min Act: -0.1700

Data Index: 999715 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0501. Min Act: -0.1700

Data Index: 256210 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0185. Min Act: -0.1700

Data Index: 150713 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0343. Min Act: -0.1700

Data Index: 986121 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1334054 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0659. Min Act: -0.1700

Data Index: 1096215 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0185. Min Act: -0.1700

Data Index: 1249235 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0343. Min Act: -0.1700

Data Index: 963419 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 3.2077. Min Range: -3.2077

Max Act: 2.9553. Min Act: -0.1700

Data Index: 631477 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.2077. Min Range: -3.2077

Max Act: 3.0027. Min Act: -0.1700

Data Index: 1260188 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 3.2077. Min Range: -3.2077

Max Act: 2.9869. Min Act: -0.1700

Data Index: 1099551 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.2077. Min Range: -3.2077

Max Act: 2.9869. Min Act: -0.1700

Data Index: 930923 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 3.2077. Min Range: -3.2077

Max Act: 2.9869. Min Act: -0.1700

Data Index: 629697 (C4 (Web Text))

Max Activating Token Index: 113