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

Dataset: Open Web Text

Neuron 1346 in Layer 3

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: 3.1897. Min Range: -3.1897

Max Act: 3.1897. Min Act: -0.1700

Data Index: 6104509 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1737. Min Act: -0.1700

Data Index: 1832195 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1485. Min Act: -0.1700

Data Index: 134736 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1320. Min Act: -0.1700

Data Index: 8802772 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1579. Min Act: -0.1700

Data Index: 4063818 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1407. Min Act: -0.1700

Data Index: 1702070 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1191. Min Act: -0.1700

Data Index: 3366002 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1288. Min Act: -0.1700

Data Index: 5545247 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1134. Min Act: -0.1700

Data Index: 6696664 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1219. Min Act: -0.1700

Data Index: 2303099 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1081. Min Act: -0.1700

Data Index: 8571738 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1140. Min Act: -0.1700

Data Index: 6950272 (Open Web Text)

Max Activating Token Index: 624

Text #12

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.1006. Min Act: -0.1700

Data Index: 7364709 (Open Web Text)

Max Activating Token Index: 586

Text #13

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0577. Min Act: -0.1700

Data Index: 133717 (Open Web Text)

Max Activating Token Index: 776

Text #14

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0708. Min Act: -0.1700

Data Index: 4468022 (Open Web Text)

Max Activating Token Index: 619

Text #15

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0743. Min Act: -0.1700

Data Index: 3245109 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0822. Min Act: -0.1700

Data Index: 77108 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0736. Min Act: -0.1700

Data Index: 2277307 (Open Web Text)

Max Activating Token Index: 118

Text #18

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0649. Min Act: -0.1700

Data Index: 4148087 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 3.1897. Min Range: -3.1897

Max Act: 3.0697. Min Act: -0.1700

Data Index: 6297169 (Open Web Text)

Max Activating Token Index: 632