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

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

Neuron 946 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: 3.7953. Min Range: -3.7953

Max Act: 3.7640. Min Act: -0.1700

Data Index: 312769 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.7953. Min Act: -0.1700

Data Index: 1165209 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.7953. Min Act: -0.1700

Data Index: 1018185 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.7640. Min Act: -0.1700

Data Index: 875029 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.6701. Min Act: -0.1700

Data Index: 1563216 (Python Code)

Max Activating Token Index: 530

Text #5

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.6701. Min Act: -0.1700

Data Index: 847999 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.6701. Min Act: -0.1700

Data Index: 1295632 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.6388. Min Act: -0.1700

Data Index: 1455113 (Python Code)

Max Activating Token Index: 206

Text #8

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.6701. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 751

Text #9

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5762. Min Act: -0.1700

Data Index: 1030358 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.6075. Min Act: -0.1700

Data Index: 227915 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5762. Min Act: -0.1700

Data Index: 1025581 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5135. Min Act: -0.1700

Data Index: 282594 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5762. Min Act: -0.1700

Data Index: 1135136 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5449. Min Act: -0.1700

Data Index: 973846 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5135. Min Act: -0.1700

Data Index: 1182827 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5449. Min Act: -0.1700

Data Index: 740441 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5135. Min Act: -0.1700

Data Index: 1024520 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5135. Min Act: -0.1700

Data Index: 1153110 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.5135. Min Act: -0.1700

Data Index: 650502 (C4 (Web Text))

Max Activating Token Index: 1000