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

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

Neuron 715 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: 3.8948. Min Range: -3.8948

Max Act: 3.8948. Min Act: -0.1700

Data Index: 1231397 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.8948. Min Act: -0.1700

Data Index: 332817 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.8323. Min Act: -0.1700

Data Index: 1202015 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7697. Min Act: -0.1700

Data Index: 132090 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.8323. Min Act: -0.1700

Data Index: 1037782 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.8010. Min Act: -0.1700

Data Index: 1332780 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7384. Min Act: -0.1700

Data Index: 114371 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.8323. Min Act: -0.1700

Data Index: 1122027 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.8010. Min Act: -0.1700

Data Index: 124855 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7384. Min Act: -0.1700

Data Index: 419118 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7697. Min Act: -0.1700

Data Index: 526065 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7384. Min Act: -0.1700

Data Index: 263262 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7384. Min Act: -0.1700

Data Index: 362074 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7697. Min Act: -0.1700

Data Index: 235845 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7384. Min Act: -0.1700

Data Index: 12718 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7071. Min Act: -0.1700

Data Index: 213794 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7071. Min Act: -0.1700

Data Index: 857309 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7384. Min Act: -0.1700

Data Index: 307064 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7071. Min Act: -0.1700

Data Index: 908827 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.8948. Min Range: -3.8948

Max Act: 3.7071. Min Act: -0.1700

Data Index: 449656 (C4 (Web Text))

Max Activating Token Index: 623