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

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

Neuron 106 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: 3.7141. Min Range: -3.7141

Max Act: 3.7141. Min Act: -0.1700

Data Index: 1280801 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.6515. Min Act: -0.1700

Data Index: 471253 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.6515. Min Act: -0.1700

Data Index: 244953 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.6515. Min Act: -0.1700

Data Index: 343954 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5888. Min Act: -0.1700

Data Index: 317492 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1148313 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.6201. Min Act: -0.1700

Data Index: 21552 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5575. Min Act: -0.1700

Data Index: 391788 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5888. Min Act: -0.1700

Data Index: 518228 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5575. Min Act: -0.1700

Data Index: 62966 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5888. Min Act: -0.1700

Data Index: 1180970 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5888. Min Act: -0.1700

Data Index: 443057 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5262. Min Act: -0.1700

Data Index: 563890 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.4949. Min Act: -0.1700

Data Index: 390439 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5262. Min Act: -0.1700

Data Index: 170006 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5262. Min Act: -0.1700

Data Index: 770578 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5575. Min Act: -0.1700

Data Index: 726256 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5575. Min Act: -0.1700

Data Index: 702400 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5262. Min Act: -0.1700

Data Index: 610275 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.7141. Min Range: -3.7141

Max Act: 3.5262. Min Act: -0.1700

Data Index: 227225 (C4 (Web Text))

Max Activating Token Index: 940