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

Dataset: Open Web Text

Neuron 2193 in Layer 4

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: 5.4753. Min Range: -5.4753

Max Act: 5.4753. Min Act: -0.1700

Data Index: 5227338 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.3826. Min Act: -0.1700

Data Index: 378649 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.1235. Min Act: -0.1700

Data Index: 3758818 (Open Web Text)

Max Activating Token Index: 286

Text #3

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.1186. Min Act: -0.1700

Data Index: 6334686 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.1247. Min Act: -0.1700

Data Index: 2788958 (Open Web Text)

Max Activating Token Index: 165

Text #5

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.0352. Min Act: -0.1700

Data Index: 2438907 (Open Web Text)

Max Activating Token Index: 157

Text #6

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.0547. Min Act: -0.1700

Data Index: 8580326 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.0206. Min Act: -0.1700

Data Index: 6271743 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 5.4753. Min Range: -5.4753

Max Act: 5.0393. Min Act: -0.1700

Data Index: 2592096 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9580. Min Act: -0.1700

Data Index: 7257021 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9321. Min Act: -0.1700

Data Index: 7333073 (Open Web Text)

Max Activating Token Index: 238

Text #11

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9343. Min Act: -0.1700

Data Index: 8129852 (Open Web Text)

Max Activating Token Index: 472

Text #12

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9733. Min Act: -0.1700

Data Index: 1270245 (Open Web Text)

Max Activating Token Index: 147

Text #13

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9382. Min Act: -0.1700

Data Index: 3619509 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.8654. Min Act: -0.1700

Data Index: 674074 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9512. Min Act: -0.1700

Data Index: 116565 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9075. Min Act: -0.1700

Data Index: 8265993 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9196. Min Act: -0.1700

Data Index: 992204 (Open Web Text)

Max Activating Token Index: 634

Text #18

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9077. Min Act: -0.1700

Data Index: 771609 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 5.4753. Min Range: -5.4753

Max Act: 4.9043. Min Act: -0.1700

Data Index: 847180 (Open Web Text)

Max Activating Token Index: 886