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

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

Neuron 1961 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: 3.4689. Min Range: -3.4689

Max Act: 3.4689. Min Act: -0.1700

Data Index: 5164 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4689. Min Act: -0.1700

Data Index: 163125 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4689. Min Act: -0.1700

Data Index: 421097 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3748. Min Act: -0.1700

Data Index: 1240026 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4062. Min Act: -0.1700

Data Index: 621151 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3748. Min Act: -0.1700

Data Index: 1288108 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3748. Min Act: -0.1700

Data Index: 710232 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3748. Min Act: -0.1700

Data Index: 1113259 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4062. Min Act: -0.1700

Data Index: 210759 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3748. Min Act: -0.1700

Data Index: 703294 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 83097 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3434. Min Act: -0.1700

Data Index: 780872 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3748. Min Act: -0.1700

Data Index: 151943 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 1320396 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3434. Min Act: -0.1700

Data Index: 1108524 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 127416 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 1017682 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 4623 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 1006495 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3120. Min Act: -0.1700

Data Index: 307101 (C4 (Web Text))

Max Activating Token Index: 355