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

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

Neuron 338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4787. Min Act: -0.1700

Data Index: 741406 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4944. Min Act: -0.1700

Data Index: 625190 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4474. Min Act: -0.1700

Data Index: 1153897 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4160. Min Act: -0.1700

Data Index: 919423 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4317. Min Act: -0.1700

Data Index: 2783 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4160. Min Act: -0.1700

Data Index: 453630 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.4003. Min Act: -0.1700

Data Index: 1356906 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3376. Min Act: -0.1700

Data Index: 477641 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1095259 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3690. Min Act: -0.1700

Data Index: 1041371 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3847. Min Act: -0.1700

Data Index: 30754 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3533. Min Act: -0.1700

Data Index: 583604 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3847. Min Act: -0.1700

Data Index: 1231262 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3376. Min Act: -0.1700

Data Index: 1005996 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.2748. Min Act: -0.1700

Data Index: 1053395 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3533. Min Act: -0.1700

Data Index: 578146 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3062. Min Act: -0.1700

Data Index: 660178 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3219. Min Act: -0.1700

Data Index: 891220 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1030632 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 3.4944. Min Range: -3.4944

Max Act: 3.3533. Min Act: -0.1700

Data Index: 439031 (C4 (Web Text))

Max Activating Token Index: 413