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

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

Neuron 540 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0040. Min Act: -0.1700

Data Index: 654739 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0198. Min Act: -0.1700

Data Index: 195875 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0198. Min Act: -0.1700

Data Index: 574782 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0040. Min Act: -0.1700

Data Index: 73696 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9248. Min Act: -0.1700

Data Index: 681870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9565. Min Act: -0.1700

Data Index: 822932 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0198. Min Act: -0.1700

Data Index: 599153 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0040. Min Act: -0.1700

Data Index: 231119 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9881. Min Act: -0.1700

Data Index: 1141574 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9723. Min Act: -0.1700

Data Index: 1023152 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9881. Min Act: -0.1700

Data Index: 1203639 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9723. Min Act: -0.1700

Data Index: 1330474 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9565. Min Act: -0.1700

Data Index: 1159967 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9881. Min Act: -0.1700

Data Index: 633973 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9565. Min Act: -0.1700

Data Index: 569124 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9565. Min Act: -0.1700

Data Index: 305704 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 3.0198. Min Range: -3.0198

Max Act: 3.0198. Min Act: -0.1700

Data Index: 937891 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9248. Min Act: -0.1700

Data Index: 95841 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9565. Min Act: -0.1700

Data Index: 949388 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9248. Min Act: -0.1700

Data Index: 770744 (C4 (Web Text))

Max Activating Token Index: 629