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

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

Neuron 1589 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: 3.3948. Min Range: -3.3948

Max Act: 3.3948. Min Act: -0.1700

Data Index: 284344 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.2535. Min Act: -0.1700

Data Index: 54013 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.2220. Min Act: -0.1700

Data Index: 360089 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.2220. Min Act: -0.1700

Data Index: 923355 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1906. Min Act: -0.1700

Data Index: 737847 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1748. Min Act: -0.1700

Data Index: 674102 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1591. Min Act: -0.1700

Data Index: 180586 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1591. Min Act: -0.1700

Data Index: 776149 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1276. Min Act: -0.1700

Data Index: 718310 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1276. Min Act: -0.1700

Data Index: 969827 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1276. Min Act: -0.1700

Data Index: 1046334 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1276. Min Act: -0.1700

Data Index: 1190818 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1276. Min Act: -0.1700

Data Index: 300968 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1118. Min Act: -0.1700

Data Index: 1359650 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1118. Min Act: -0.1700

Data Index: 615919 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.0961. Min Act: -0.1700

Data Index: 545270 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.1118. Min Act: -0.1700

Data Index: 772570 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.0961. Min Act: -0.1700

Data Index: 97366 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.0961. Min Act: -0.1700

Data Index: 478329 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.3948. Min Range: -3.3948

Max Act: 3.0961. Min Act: -0.1700

Data Index: 487194 (C4 (Web Text))

Max Activating Token Index: 310