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

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

Neuron 1968 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.7700. Min Act: -0.1700

Data Index: 10203 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.7543. Min Act: -0.1700

Data Index: 1327178 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6918. Min Act: -0.1700

Data Index: 1326208 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.6761. Min Act: -0.1700

Data Index: 936177 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5978. Min Act: -0.1700

Data Index: 57046 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5822. Min Act: -0.1700

Data Index: 410964 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5665. Min Act: -0.1700

Data Index: 720855 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5665. Min Act: -0.1700

Data Index: 124390 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5822. Min Act: -0.1700

Data Index: 1046225 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5665. Min Act: -0.1700

Data Index: 1319270 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5665. Min Act: -0.1700

Data Index: 1309676 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5509. Min Act: -0.1700

Data Index: 1293497 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5509. Min Act: -0.1700

Data Index: 1054010 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5509. Min Act: -0.1700

Data Index: 1081376 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5665. Min Act: -0.1700

Data Index: 99078 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5665. Min Act: -0.1700

Data Index: 30394 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5352. Min Act: -0.1700

Data Index: 680673 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5352. Min Act: -0.1700

Data Index: 313372 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5195. Min Act: -0.1700

Data Index: 78741 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 3.7700. Min Range: -3.7700

Max Act: 3.5195. Min Act: -0.1700

Data Index: 784920 (C4 (Web Text))

Max Activating Token Index: 391