Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1960 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4991. Min Act: -0.1700

Data Index: 581365 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4521. Min Act: -0.1700

Data Index: 1010213 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4207. Min Act: -0.1700

Data Index: 1152819 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4207. Min Act: -0.1700

Data Index: 144092 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3893. Min Act: -0.1700

Data Index: 1218503 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3893. Min Act: -0.1700

Data Index: 759579 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3737. Min Act: -0.1700

Data Index: 51240 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3580. Min Act: -0.1700

Data Index: 747387 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3580. Min Act: -0.1700

Data Index: 641670 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3580. Min Act: -0.1700

Data Index: 857779 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3580. Min Act: -0.1700

Data Index: 1161267 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3580. Min Act: -0.1700

Data Index: 190108 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3580. Min Act: -0.1700

Data Index: 816907 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3423. Min Act: -0.1700

Data Index: 1158027 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3423. Min Act: -0.1700

Data Index: 1346747 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3423. Min Act: -0.1700

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3266. Min Act: -0.1700

Data Index: 884385 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3266. Min Act: -0.1700

Data Index: 448615 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3266. Min Act: -0.1700

Data Index: 57479 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3423. Min Act: -0.1700

Data Index: 743829 (C4 (Web Text))

Max Activating Token Index: 426