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

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

Neuron 1956 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: 3.0014. Min Range: -3.0014

Max Act: 3.0014. Min Act: -0.1700

Data Index: 582063 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9856. Min Act: -0.1700

Data Index: 608935 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9698. Min Act: -0.1700

Data Index: 363702 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9698. Min Act: -0.1700

Data Index: 182039 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9540. Min Act: -0.1700

Data Index: 242196 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9698. Min Act: -0.1700

Data Index: 313244 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 29685 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9223. Min Act: -0.1700

Data Index: 694513 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9381. Min Act: -0.1700

Data Index: 644586 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9223. Min Act: -0.1700

Data Index: 1038321 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 1081657 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 271664 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 564514 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 706938 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 747256 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.8906. Min Act: -0.1700

Data Index: 789566 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.8906. Min Act: -0.1700

Data Index: 593285 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.9064. Min Act: -0.1700

Data Index: 330051 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.8906. Min Act: -0.1700

Data Index: 245086 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 3.0014. Min Range: -3.0014

Max Act: 2.8747. Min Act: -0.1700

Data Index: 427256 (C4 (Web Text))

Max Activating Token Index: 474