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

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

Neuron 1106 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.9048. Min Act: -0.1700

Data Index: 1537500 (Python Code)

Max Activating Token Index: 246

Text #1

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.8735. Min Act: -0.1700

Data Index: 460912 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7953. Min Act: -0.1700

Data Index: 1011918 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7796. Min Act: -0.1699

Data Index: 884425 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7640. Min Act: -0.1700

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7953. Min Act: -0.1700

Data Index: 493518 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7484. Min Act: -0.1700

Data Index: 294569 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7484. Min Act: -0.1700

Data Index: 1537687 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7484. Min Act: -0.1700

Data Index: 564299 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7327. Min Act: -0.1700

Data Index: 971813 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7171. Min Act: -0.1700

Data Index: 1301764 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.7014. Min Act: -0.1700

Data Index: 228597 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6701. Min Act: -0.1700

Data Index: 852646 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6858. Min Act: -0.1700

Data Index: 965882 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6701. Min Act: -0.1700

Data Index: 85265 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6545. Min Act: -0.1700

Data Index: 1297643 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6701. Min Act: -0.1700

Data Index: 52696 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6545. Min Act: -0.1700

Data Index: 494183 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6388. Min Act: -0.1700

Data Index: 1122739 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 3.9048. Min Range: -3.9048

Max Act: 3.6701. Min Act: -0.1700

Data Index: 205443 (C4 (Web Text))

Max Activating Token Index: 216