Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1436 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.4163. Min Range: -4.4163

Max Act: 4.4163. Min Act: -0.1700

Data Index: 1323085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.5719. Min Act: -0.1700

Data Index: 1524107 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1405057 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.4309. Min Act: -0.1700

Data Index: 704429 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.4466. Min Act: -0.1700

Data Index: 118091 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3682. Min Act: -0.1700

Data Index: 188357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3839. Min Act: -0.1700

Data Index: 852524 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3525. Min Act: -0.1700

Data Index: 1075331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.2897. Min Act: -0.1700

Data Index: 225173 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.2897. Min Act: -0.1700

Data Index: 1192585 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3211. Min Act: -0.1700

Data Index: 1316670 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3368. Min Act: -0.1700

Data Index: 658252 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.2740. Min Act: -0.1700

Data Index: 110514 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.2740. Min Act: -0.1700

Data Index: 1077796 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3368. Min Act: -0.1700

Data Index: 1004225 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1651375 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.2897. Min Act: -0.1700

Data Index: 357330 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3211. Min Act: -0.1700

Data Index: 112691 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.2897. Min Act: -0.1700

Data Index: 365513 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 4.4163. Min Range: -4.4163

Max Act: 3.3368. Min Act: -0.1700

Data Index: 494101 (C4 (Web Text))

Max Activating Token Index: 559