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

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

Neuron 587 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: 3.4112. Min Range: -3.4112

Max Act: 3.4112. Min Act: -0.1700

Data Index: 1666 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3799. Min Act: -0.1700

Data Index: 1667 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3171. Min Act: -0.1700

Data Index: 195808 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3485. Min Act: -0.1700

Data Index: 1026688 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3171. Min Act: -0.1700

Data Index: 443813 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3485. Min Act: -0.1700

Data Index: 696002 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3328. Min Act: -0.1700

Data Index: 903986 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3328. Min Act: -0.1700

Data Index: 1039245 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3014. Min Act: -0.1700

Data Index: 815116 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2700. Min Act: -0.1700

Data Index: 1135518 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2857. Min Act: -0.1700

Data Index: 751269 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2700. Min Act: -0.1700

Data Index: 549908 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2542. Min Act: -0.1700

Data Index: 654809 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2385. Min Act: -0.1700

Data Index: 878959 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2542. Min Act: -0.1700

Data Index: 329328 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3171. Min Act: -0.1700

Data Index: 1056004 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.3014. Min Act: -0.1700

Data Index: 759686 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2385. Min Act: -0.1700

Data Index: 495185 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2228. Min Act: -0.1700

Data Index: 699509 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2071. Min Act: -0.1700

Data Index: 945097 (C4 (Web Text))

Max Activating Token Index: 450