Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2720 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.8737. Min Act: -0.1700

Data Index: 6083039 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.8144. Min Act: -0.1700

Data Index: 1065387 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.8141. Min Act: -0.1700

Data Index: 1065386 (Open Web Text)

Max Activating Token Index: 652

Text #3

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.8121. Min Act: -0.1700

Data Index: 4965485 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.7414. Min Act: -0.1700

Data Index: 1065385 (Open Web Text)

Max Activating Token Index: 412

Text #5

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.7210. Min Act: -0.1700

Data Index: 5641492 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.7046. Min Act: -0.1700

Data Index: 3949252 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.7318. Min Act: -0.1700

Data Index: 4689360 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.6899. Min Act: -0.1700

Data Index: 1686293 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.7058. Min Act: -0.1700

Data Index: 6220815 (Open Web Text)

Max Activating Token Index: 215

Text #10

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.6920. Min Act: -0.1700

Data Index: 3949250 (Open Web Text)

Max Activating Token Index: 148

Text #11

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.6799. Min Act: -0.1700

Data Index: 5425890 (Open Web Text)

Max Activating Token Index: 666

Text #12

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.6834. Min Act: -0.1700

Data Index: 379418 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.5713. Min Act: -0.1700

Data Index: 6109219 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.6376. Min Act: -0.1700

Data Index: 2819731 (Open Web Text)

Max Activating Token Index: 767

Text #15

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.5448. Min Act: -0.1700

Data Index: 8095164 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.6156. Min Act: -0.1700

Data Index: 6220832 (Open Web Text)

Max Activating Token Index: 265

Text #17

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.5161. Min Act: -0.1700

Data Index: 8108477 (Open Web Text)

Max Activating Token Index: 631

Text #18

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.5426. Min Act: -0.1700

Data Index: 6220817 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 4.8737. Min Range: -4.8737

Max Act: 4.5415. Min Act: -0.1700

Data Index: 2763985 (Open Web Text)

Max Activating Token Index: 487