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

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

Neuron 457 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: 3.8917. Min Range: -3.8917

Max Act: 3.8917. Min Act: -0.1700

Data Index: 1236738 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.7666. Min Act: -0.1700

Data Index: 1335569 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.7353. Min Act: -0.1700

Data Index: 720403 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.7353. Min Act: -0.1700

Data Index: 235717 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.7353. Min Act: -0.1700

Data Index: 1142145 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.6414. Min Act: -0.1700

Data Index: 457907 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1165536 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.6101. Min Act: -0.1700

Data Index: 24223 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.6101. Min Act: -0.1700

Data Index: 548542 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.6414. Min Act: -0.1700

Data Index: 1151385 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5788. Min Act: -0.1700

Data Index: 591394 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5475. Min Act: -0.1700

Data Index: 266283 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5788. Min Act: -0.1700

Data Index: 235076 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5788. Min Act: -0.1700

Data Index: 112987 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5788. Min Act: -0.1700

Data Index: 116981 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5475. Min Act: -0.1700

Data Index: 578011 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5475. Min Act: -0.1700

Data Index: 943481 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5161. Min Act: -0.1700

Data Index: 680144 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5475. Min Act: -0.1700

Data Index: 63972 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.8917. Min Range: -3.8917

Max Act: 3.5475. Min Act: -0.1700

Data Index: 1058099 (C4 (Web Text))

Max Activating Token Index: 997