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

Dataset: Open Web Text

Neuron 1875 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: 1.6196. Min Range: -1.6196

Max Act: 1.6196. Min Act: -0.1700

Data Index: 8607697 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5961. Min Act: -0.1698

Data Index: 6454854 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5678. Min Act: -0.1699

Data Index: 1165913 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5416. Min Act: -0.1700

Data Index: 6635916 (Open Web Text)

Max Activating Token Index: 936

Text #4

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5585. Min Act: -0.1699

Data Index: 5700532 (Open Web Text)

Max Activating Token Index: 538

Text #5

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5511. Min Act: -0.1700

Data Index: 7941858 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5423. Min Act: -0.1700

Data Index: 2607074 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5401. Min Act: -0.1700

Data Index: 7914286 (Open Web Text)

Max Activating Token Index: 68

Text #8

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5302. Min Act: -0.1700

Data Index: 4252262 (Open Web Text)

Max Activating Token Index: 845

Text #9

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5292. Min Act: -0.1698

Data Index: 2055064 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5199. Min Act: -0.1700

Data Index: 540316 (Open Web Text)

Max Activating Token Index: 282

Text #11

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5213. Min Act: -0.1700

Data Index: 1361681 (Open Web Text)

Max Activating Token Index: 163

Text #12

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5240. Min Act: -0.1700

Data Index: 2596768 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5110. Min Act: -0.1692

Data Index: 6165937 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5048. Min Act: -0.1700

Data Index: 2300918 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5166. Min Act: -0.1689

Data Index: 5586071 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5086. Min Act: -0.1700

Data Index: 2744345 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5066. Min Act: -0.1700

Data Index: 187842 (Open Web Text)

Max Activating Token Index: 113

Text #18

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.4957. Min Act: -0.1700

Data Index: 8020554 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 1.6196. Min Range: -1.6196

Max Act: 1.5131. Min Act: -0.1700

Data Index: 2423402 (Open Web Text)

Max Activating Token Index: 112