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

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

Neuron 1188 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.8939. Min Act: -0.1700

Data Index: 141357 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.7062. Min Act: -0.1700

Data Index: 684006 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6749. Min Act: -0.1700

Data Index: 78034 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6123. Min Act: -0.1700

Data Index: 36895 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5810. Min Act: -0.1700

Data Index: 900774 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5184. Min Act: -0.1700

Data Index: 210728 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5810. Min Act: -0.1700

Data Index: 249392 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6123. Min Act: -0.1700

Data Index: 315832 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6123. Min Act: -0.1700

Data Index: 756440 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6123. Min Act: -0.1700

Data Index: 906203 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6436. Min Act: -0.1700

Data Index: 171656 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5810. Min Act: -0.1700

Data Index: 565380 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5810. Min Act: -0.1700

Data Index: 229809 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5497. Min Act: -0.1700

Data Index: 177087 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6123. Min Act: -0.1700

Data Index: 954499 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5497. Min Act: -0.1700

Data Index: 575696 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.6436. Min Act: -0.1700

Data Index: 842271 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5810. Min Act: -0.1700

Data Index: 553034 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5810. Min Act: -0.1700

Data Index: 566135 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.8939. Min Range: -3.8939

Max Act: 3.5497. Min Act: -0.1700

Data Index: 620472 (C4 (Web Text))

Max Activating Token Index: 794