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

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

Neuron 1090 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.3700. Min Act: -0.1700

Data Index: 606639 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.2915. Min Act: -0.1700

Data Index: 828650 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.2444. Min Act: -0.1700

Data Index: 471203 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.2286. Min Act: -0.1700

Data Index: 1175007 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1814. Min Act: -0.1700

Data Index: 1619833 (Python Code)

Max Activating Token Index: 894

Text #5

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1657. Min Act: -0.1700

Data Index: 843519 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1342. Min Act: -0.1700

Data Index: 245224 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1342. Min Act: -0.1700

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1342. Min Act: -0.1700

Data Index: 589754 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1342. Min Act: -0.1700

Data Index: 814505 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.0869. Min Act: -0.1700

Data Index: 981341 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1027. Min Act: -0.1700

Data Index: 514098 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1184. Min Act: -0.1700

Data Index: 618654 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1027. Min Act: -0.1700

Data Index: 188451 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1027. Min Act: -0.1700

Data Index: 438200 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.0080. Min Act: -0.1700

Data Index: 1358479 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.1027. Min Act: -0.1700

Data Index: 227803 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.0869. Min Act: -0.1700

Data Index: 1326364 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.0711. Min Act: -0.1700

Data Index: 780502 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 3.3700. Min Range: -3.3700

Max Act: 3.0869. Min Act: -0.1700

Data Index: 434650 (C4 (Web Text))

Max Activating Token Index: 812