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

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

Neuron 1407 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: 3.2632. Min Range: -3.2632

Max Act: 3.2632. Min Act: -0.1700

Data Index: 605612 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2632. Min Act: -0.1700

Data Index: 902577 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2161. Min Act: -0.1700

Data Index: 81893 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2003. Min Act: -0.1700

Data Index: 1255492 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2003. Min Act: -0.1700

Data Index: 227457 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2003. Min Act: -0.1700

Data Index: 1223800 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2161. Min Act: -0.1700

Data Index: 266996 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2003. Min Act: -0.1700

Data Index: 83924 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1846. Min Act: -0.1700

Data Index: 780213 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2318. Min Act: -0.1700

Data Index: 1136033 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1689. Min Act: -0.1700

Data Index: 804350 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1140131 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1374. Min Act: -0.1700

Data Index: 1110622 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1216. Min Act: -0.1700

Data Index: 1262935 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1374. Min Act: -0.1700

Data Index: 1192193 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1216. Min Act: -0.1700

Data Index: 21314 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0743. Min Act: -0.1700

Data Index: 201987 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1058. Min Act: -0.1700

Data Index: 830938 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0743. Min Act: -0.1700

Data Index: 346020 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.0901. Min Act: -0.1700

Data Index: 500215 (C4 (Web Text))

Max Activating Token Index: 830