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

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

Neuron 1738 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1093. Min Range: -4.1093

Max Act: 4.1093. Min Act: -0.1700

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 4.1093. Min Range: -4.1093

Max Act: 4.0936. Min Act: -0.1700

Data Index: 165928 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.9686. Min Act: -0.1700

Data Index: 829132 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.9373. Min Act: -0.1700

Data Index: 827958 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.9373. Min Act: -0.1700

Data Index: 997312 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.9061. Min Act: -0.1700

Data Index: 719787 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.9061. Min Act: -0.1700

Data Index: 425024 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8748. Min Act: -0.1700

Data Index: 796299 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8748. Min Act: -0.1700

Data Index: 489063 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8748. Min Act: -0.1700

Data Index: 1156265 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.9061. Min Act: -0.1700

Data Index: 1017599 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8904. Min Act: -0.1700

Data Index: 681497 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8591. Min Act: -0.1700

Data Index: 542258 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8904. Min Act: -0.1700

Data Index: 1073294 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8279. Min Act: -0.1700

Data Index: 51929 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8435. Min Act: -0.1700

Data Index: 1303727 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8435. Min Act: -0.1700

Data Index: 1019528 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8279. Min Act: -0.1700

Data Index: 862777 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8279. Min Act: -0.1700

Data Index: 708957 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 4.1093. Min Range: -4.1093

Max Act: 3.8122. Min Act: -0.1700

Data Index: 783835 (C4 (Web Text))

Max Activating Token Index: 248