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

Dataset: Open Web Text

Neuron 309 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: 3.6694. Min Range: -3.6694

Max Act: 3.6694. Min Act: -0.1700

Data Index: 3645194 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4955. Min Act: -0.1700

Data Index: 5062480 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.5094. Min Act: -0.1700

Data Index: 4629298 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4346. Min Act: -0.1700

Data Index: 2943221 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.4253. Min Act: -0.1700

Data Index: 4696947 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3840. Min Act: -0.1700

Data Index: 4497538 (Open Web Text)

Max Activating Token Index: 387

Text #6

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3675. Min Act: -0.1700

Data Index: 7142169 (Open Web Text)

Max Activating Token Index: 417

Text #7

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3596. Min Act: -0.1700

Data Index: 66505 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3589. Min Act: -0.1700

Data Index: 7282059 (Open Web Text)

Max Activating Token Index: 861

Text #9

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3486. Min Act: -0.1700

Data Index: 6811319 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3472. Min Act: -0.1700

Data Index: 50541 (Open Web Text)

Max Activating Token Index: 304

Text #11

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3202. Min Act: -0.1700

Data Index: 2712305 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3188. Min Act: -0.1700

Data Index: 8040801 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3303. Min Act: -0.1700

Data Index: 7399644 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3052. Min Act: -0.1700

Data Index: 444280 (Open Web Text)

Max Activating Token Index: 159

Text #15

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3019. Min Act: -0.1700

Data Index: 1532386 (Open Web Text)

Max Activating Token Index: 467

Text #16

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.2921. Min Act: -0.1700

Data Index: 4002475 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3083. Min Act: -0.1700

Data Index: 8605216 (Open Web Text)

Max Activating Token Index: 203

Text #18

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3135. Min Act: -0.1700

Data Index: 4005860 (Open Web Text)

Max Activating Token Index: 797

Text #19

Max Range: 3.6694. Min Range: -3.6694

Max Act: 3.3006. Min Act: -0.1700

Data Index: 3138723 (Open Web Text)

Max Activating Token Index: 505