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

Dataset: Open Web Text

Neuron 1371 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: 5.0555. Min Range: -5.0555

Max Act: 5.0555. Min Act: -0.1700

Data Index: 3363798 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 5.0555. Min Range: -5.0555

Max Act: 5.0020. Min Act: -0.1700

Data Index: 4129975 (Open Web Text)

Max Activating Token Index: 35

Text #2

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.9224. Min Act: -0.1700

Data Index: 1205134 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.9020. Min Act: -0.1700

Data Index: 4722197 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8692. Min Act: -0.1700

Data Index: 4569211 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8553. Min Act: -0.1700

Data Index: 8482391 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8697. Min Act: -0.1700

Data Index: 6636919 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8203. Min Act: -0.1700

Data Index: 5243976 (Open Web Text)

Max Activating Token Index: 184

Text #8

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8479. Min Act: -0.1700

Data Index: 5301313 (Open Web Text)

Max Activating Token Index: 144

Text #9

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8315. Min Act: -0.1700

Data Index: 8162542 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8294. Min Act: -0.1700

Data Index: 3882416 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8194. Min Act: -0.1700

Data Index: 2589903 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8116. Min Act: -0.1700

Data Index: 3632039 (Open Web Text)

Max Activating Token Index: 47

Text #13

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8032. Min Act: -0.1700

Data Index: 7238932 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.7962. Min Act: -0.1700

Data Index: 4201765 (Open Web Text)

Max Activating Token Index: 810

Text #15

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8075. Min Act: -0.1700

Data Index: 8468598 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8110. Min Act: -0.1700

Data Index: 3618060 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8125. Min Act: -0.1700

Data Index: 6424683 (Open Web Text)

Max Activating Token Index: 58

Text #18

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.7829. Min Act: -0.1700

Data Index: 6272483 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 5.0555. Min Range: -5.0555

Max Act: 4.8028. Min Act: -0.1700

Data Index: 326230 (Open Web Text)

Max Activating Token Index: 311