Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1099 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.7482. Min Act: -0.1700

Data Index: 1635459 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1610469 (Python Code)

Max Activating Token Index: 462

Text #2

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.6543. Min Act: -0.1700

Data Index: 1371029 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.6386. Min Act: -0.1700

Data Index: 1547087 (Python Code)

Max Activating Token Index: 359

Text #4

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.5760. Min Act: -0.1700

Data Index: 1360273 (Python Code)

Max Activating Token Index: 391

Text #5

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.5290. Min Act: -0.1700

Data Index: 1460028 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4507. Min Act: -0.1700

Data Index: 616053 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4350. Min Act: -0.1700

Data Index: 62584 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4507. Min Act: -0.1700

Data Index: 294078 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4350. Min Act: -0.1700

Data Index: 191685 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4193. Min Act: -0.1700

Data Index: 745036 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.4036. Min Act: -0.1700

Data Index: 1190118 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3879. Min Act: -0.1700

Data Index: 1288073 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3565. Min Act: -0.1700

Data Index: 1357387 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3722. Min Act: -0.1700

Data Index: 716777 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3722. Min Act: -0.1700

Data Index: 722131 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3722. Min Act: -0.1700

Data Index: 246131 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.2937. Min Act: -0.1700

Data Index: 836666 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3252. Min Act: -0.1700

Data Index: 1302503 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 3.7794. Min Range: -3.7794

Max Act: 3.3409. Min Act: -0.1700

Data Index: 639313 (C4 (Web Text))

Max Activating Token Index: 800