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

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

Neuron 154 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: 3.3179. Min Range: -3.3179

Max Act: 3.3022. Min Act: -0.1700

Data Index: 695761 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.3022. Min Act: -0.1700

Data Index: 128260 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.3179. Min Act: -0.1700

Data Index: 1046437 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2708. Min Act: -0.1700

Data Index: 1233387 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2865. Min Act: -0.1700

Data Index: 924954 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2236. Min Act: -0.1700

Data Index: 1199430 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2393. Min Act: -0.1700

Data Index: 128689 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2550. Min Act: -0.1700

Data Index: 548354 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2393. Min Act: -0.1700

Data Index: 644257 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2079. Min Act: -0.1700

Data Index: 848795 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2236. Min Act: -0.1700

Data Index: 1113809 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.1764. Min Act: -0.1700

Data Index: 874212 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2393. Min Act: -0.1700

Data Index: 4640 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2236. Min Act: -0.1700

Data Index: 678330 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.2079. Min Act: -0.1700

Data Index: 119200 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.1607. Min Act: -0.1700

Data Index: 615925 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.1134. Min Act: -0.1700

Data Index: 560358 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.1292. Min Act: -0.1700

Data Index: 693963 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.0976. Min Act: -0.1700

Data Index: 910367 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 3.3179. Min Range: -3.3179

Max Act: 3.1449. Min Act: -0.1700

Data Index: 1577285 (Python Code)

Max Activating Token Index: 137