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

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

Neuron 1041 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: 3.5013. Min Range: -3.5013

Max Act: 3.5013. Min Act: -0.1700

Data Index: 833551 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.4543. Min Act: -0.1700

Data Index: 817124 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.3759. Min Act: -0.1700

Data Index: 1277793 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.3445. Min Act: -0.1700

Data Index: 562875 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.3131. Min Act: -0.1700

Data Index: 1286211 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.3131. Min Act: -0.1700

Data Index: 971324 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.3131. Min Act: -0.1700

Data Index: 1111974 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.3288. Min Act: -0.1700

Data Index: 426438 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2974. Min Act: -0.1700

Data Index: 898311 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2974. Min Act: -0.1700

Data Index: 684157 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2974. Min Act: -0.1700

Data Index: 509349 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2974. Min Act: -0.1700

Data Index: 569191 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2502. Min Act: -0.1700

Data Index: 952409 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2660. Min Act: -0.1700

Data Index: 1501443 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2660. Min Act: -0.1700

Data Index: 1311214 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2502. Min Act: -0.1700

Data Index: 617565 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2502. Min Act: -0.1700

Data Index: 1318381 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2345. Min Act: -0.1700

Data Index: 963501 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2188. Min Act: -0.1700

Data Index: 1101367 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 3.5013. Min Range: -3.5013

Max Act: 3.2188. Min Act: -0.1700

Data Index: 644998 (C4 (Web Text))

Max Activating Token Index: 940