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

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

Neuron 1421 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: 3.5573. Min Range: -3.5573

Max Act: 3.5573. Min Act: -0.1700

Data Index: 1149653 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.5573. Min Act: -0.1700

Data Index: 386656 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4946. Min Act: -0.1700

Data Index: 1327781 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4946. Min Act: -0.1700

Data Index: 583725 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4946. Min Act: -0.1700

Data Index: 655275 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4632. Min Act: -0.1700

Data Index: 274236 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4319. Min Act: -0.1700

Data Index: 777621 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4319. Min Act: -0.1700

Data Index: 756642 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4319. Min Act: -0.1700

Data Index: 1032597 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4005. Min Act: -0.1700

Data Index: 421358 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4319. Min Act: -0.1700

Data Index: 655377 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1223172 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4005. Min Act: -0.1700

Data Index: 325725 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3692. Min Act: -0.1700

Data Index: 915352 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3378. Min Act: -0.1700

Data Index: 710395 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3692. Min Act: -0.1700

Data Index: 1258877 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3692. Min Act: -0.1700

Data Index: 504339 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3378. Min Act: -0.1700

Data Index: 63058 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.3378. Min Act: -0.1700

Data Index: 93289 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 3.5573. Min Range: -3.5573

Max Act: 3.4005. Min Act: -0.1700

Data Index: 630471 (C4 (Web Text))

Max Activating Token Index: 807