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

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

Neuron 704 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: 3.8728. Min Range: -3.8728

Max Act: 3.8728. Min Act: -0.1700

Data Index: 56383 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.5912. Min Act: -0.1700

Data Index: 91976 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.5598. Min Act: -0.1700

Data Index: 1210675 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.5598. Min Act: -0.1700

Data Index: 861633 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.5598. Min Act: -0.1700

Data Index: 310188 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4972. Min Act: -0.1700

Data Index: 209000 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.5285. Min Act: -0.1700

Data Index: 1258062 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4972. Min Act: -0.1700

Data Index: 485233 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4658. Min Act: -0.1700

Data Index: 1312917 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1021676 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.3090. Min Act: -0.1700

Data Index: 304191 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4031. Min Act: -0.1700

Data Index: 587926 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4658. Min Act: -0.1700

Data Index: 1287862 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4345. Min Act: -0.1700

Data Index: 173517 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1188310 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.4031. Min Act: -0.1700

Data Index: 446211 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.3717. Min Act: -0.1700

Data Index: 801652 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.3404. Min Act: -0.1700

Data Index: 202680 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.3717. Min Act: -0.1700

Data Index: 1281411 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 3.8728. Min Range: -3.8728

Max Act: 3.3717. Min Act: -0.1700

Data Index: 1161251 (C4 (Web Text))

Max Activating Token Index: 564