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

Dataset: Open Web Text

Neuron 307 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: 3.6014. Min Range: -3.6014

Max Act: 3.6014. Min Act: -0.1700

Data Index: 712936 (Open Web Text)

Max Activating Token Index: 415

Text #1

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.5670. Min Act: -0.1700

Data Index: 5604501 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.5268. Min Act: -0.1700

Data Index: 2081073 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.5084. Min Act: -0.1700

Data Index: 2923579 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4982. Min Act: -0.1700

Data Index: 2658164 (Open Web Text)

Max Activating Token Index: 940

Text #5

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4854. Min Act: -0.1700

Data Index: 4299551 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4701. Min Act: -0.1700

Data Index: 7701679 (Open Web Text)

Max Activating Token Index: 266

Text #7

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4928. Min Act: -0.1700

Data Index: 6302214 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.5041. Min Act: -0.1700

Data Index: 5918111 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4917. Min Act: -0.1700

Data Index: 7260008 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4707. Min Act: -0.1700

Data Index: 5577713 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4763. Min Act: -0.1700

Data Index: 147362 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4475. Min Act: -0.1700

Data Index: 6838947 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4538. Min Act: -0.1700

Data Index: 3205352 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4236. Min Act: -0.1700

Data Index: 4255864 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4199. Min Act: -0.1700

Data Index: 2180641 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4136. Min Act: -0.1700

Data Index: 4000290 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4220. Min Act: -0.1700

Data Index: 6244430 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4172. Min Act: -0.1700

Data Index: 1205979 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 3.6014. Min Range: -3.6014

Max Act: 3.4198. Min Act: -0.1700

Data Index: 5409918 (Open Web Text)

Max Activating Token Index: 872