Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1785 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2993. Min Act: -0.1700

Data Index: 281629 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2368. Min Act: -0.1700

Data Index: 109218 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2993. Min Act: -0.1700

Data Index: 304288 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2368. Min Act: -0.1700

Data Index: 1438099 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2056. Min Act: -0.1700

Data Index: 1176083 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2056. Min Act: -0.1700

Data Index: 378422 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1118. Min Act: -0.1700

Data Index: 1478193 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.2056. Min Act: -0.1700

Data Index: 1139065 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1431. Min Act: -0.1700

Data Index: 109363 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1743. Min Act: -0.1700

Data Index: 121581 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1431. Min Act: -0.1700

Data Index: 360272 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1431. Min Act: -0.1700

Data Index: 81199 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1118. Min Act: -0.1700

Data Index: 1499579 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1743. Min Act: -0.1700

Data Index: 655364 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1118. Min Act: -0.1700

Data Index: 816090 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.1118. Min Act: -0.1700

Data Index: 630737 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.0493. Min Act: -0.1700

Data Index: 854305 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 5.2993. Min Range: -5.2993

Max Act: 4.9868. Min Act: -0.1700

Data Index: 32442 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.0493. Min Act: -0.1700

Data Index: 1355568 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 5.2993. Min Range: -5.2993

Max Act: 5.0493. Min Act: -0.1700

Data Index: 75588 (C4 (Web Text))

Max Activating Token Index: 813