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

Dataset: Open Web Text

Neuron 1486 in Layer 2

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: 4.5759. Min Range: -4.5759

Max Act: 4.5759. Min Act: -0.1700

Data Index: 8580712 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1982. Min Act: -0.1700

Data Index: 1038652 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1438. Min Act: -0.1700

Data Index: 8417904 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1236. Min Act: -0.1700

Data Index: 5241347 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1311. Min Act: -0.1700

Data Index: 648656 (Open Web Text)

Max Activating Token Index: 343

Text #5

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1041. Min Act: -0.1700

Data Index: 6699828 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1170. Min Act: -0.1700

Data Index: 2386919 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0994. Min Act: -0.1700

Data Index: 6542574 (Open Web Text)

Max Activating Token Index: 143

Text #8

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1174. Min Act: -0.1700

Data Index: 2175197 (Open Web Text)

Max Activating Token Index: 676

Text #9

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0931. Min Act: -0.1700

Data Index: 8679423 (Open Web Text)

Max Activating Token Index: 75

Text #10

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.1027. Min Act: -0.1700

Data Index: 238457 (Open Web Text)

Max Activating Token Index: 544

Text #11

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0430. Min Act: -0.1700

Data Index: 7795914 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0717. Min Act: -0.1700

Data Index: 6395332 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0583. Min Act: -0.1700

Data Index: 8759209 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0592. Min Act: -0.1700

Data Index: 6137400 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0520. Min Act: -0.1700

Data Index: 5928885 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0617. Min Act: -0.1700

Data Index: 1401630 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0786. Min Act: -0.1700

Data Index: 658065 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0448. Min Act: -0.1700

Data Index: 6443740 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 4.5759. Min Range: -4.5759

Max Act: 4.0326. Min Act: -0.1700

Data Index: 2758988 (Open Web Text)

Max Activating Token Index: 436