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

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

Neuron 890 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1166381 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5675. Min Act: -0.1700

Data Index: 453715 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5362. Min Act: -0.1700

Data Index: 1290765 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5205. Min Act: -0.1700

Data Index: 109083 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5362. Min Act: -0.1700

Data Index: 723018 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5205. Min Act: -0.1700

Data Index: 1335116 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5205. Min Act: -0.1700

Data Index: 1166738 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5362. Min Act: -0.1700

Data Index: 219547 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5049. Min Act: -0.1700

Data Index: 1071018 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.5049. Min Act: -0.1700

Data Index: 7040 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4892. Min Act: -0.1700

Data Index: 723595 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4892. Min Act: -0.1700

Data Index: 900832 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4735. Min Act: -0.1700

Data Index: 7654 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4578. Min Act: -0.1700

Data Index: 736362 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4892. Min Act: -0.1700

Data Index: 466629 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4735. Min Act: -0.1700

Data Index: 1130152 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4735. Min Act: -0.1700

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4578. Min Act: -0.1700

Data Index: 460186 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4422. Min Act: -0.1700

Data Index: 962357 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 3.6458. Min Range: -3.6458

Max Act: 3.4265. Min Act: -0.1700

Data Index: 611577 (C4 (Web Text))

Max Activating Token Index: 826