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

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

Neuron 665 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: 5.0654. Min Range: -5.0654

Max Act: 5.0654. Min Act: -0.1700

Data Index: 80705 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.9092. Min Act: -0.1700

Data Index: 1215738 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.8154. Min Act: -0.1700

Data Index: 1201242 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.7842. Min Act: -0.1700

Data Index: 183423 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.7529. Min Act: -0.1700

Data Index: 283198 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.7217. Min Act: -0.1700

Data Index: 5999 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.7217. Min Act: -0.1700

Data Index: 1030473 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6904. Min Act: -0.1700

Data Index: 437598 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6904. Min Act: -0.1700

Data Index: 1111750 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.7217. Min Act: -0.1700

Data Index: 376033 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6904. Min Act: -0.1700

Data Index: 617716 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6592. Min Act: -0.1700

Data Index: 963254 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.5967. Min Act: -0.1700

Data Index: 330741 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.7217. Min Act: -0.1700

Data Index: 81100 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6904. Min Act: -0.1700

Data Index: 1190073 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6592. Min Act: -0.1700

Data Index: 516097 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6592. Min Act: -0.1700

Data Index: 438697 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6904. Min Act: -0.1700

Data Index: 141644 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.6592. Min Act: -0.1700

Data Index: 675 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 5.0654. Min Range: -5.0654

Max Act: 4.5967. Min Act: -0.1700

Data Index: 1232552 (C4 (Web Text))

Max Activating Token Index: 261