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

Dataset: Open Web Text

Neuron 2484 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: 4.0368. Min Range: -4.0368

Max Act: 4.0229. Min Act: -0.1700

Data Index: 5533379 (Open Web Text)

Max Activating Token Index: 850

Text #1

Max Range: 4.0368. Min Range: -4.0368

Max Act: 4.0368. Min Act: -0.1700

Data Index: 1543747 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9740. Min Act: -0.1700

Data Index: 308893 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9913. Min Act: -0.1700

Data Index: 7232878 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9602. Min Act: -0.1700

Data Index: 2028275 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9404. Min Act: -0.1700

Data Index: 2090285 (Open Web Text)

Max Activating Token Index: 423

Text #6

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9144. Min Act: -0.1700

Data Index: 7502452 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9171. Min Act: -0.1700

Data Index: 938586 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9159. Min Act: -0.1700

Data Index: 7229076 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8898. Min Act: -0.1700

Data Index: 3528908 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9086. Min Act: -0.1700

Data Index: 1690840 (Open Web Text)

Max Activating Token Index: 387

Text #11

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8934. Min Act: -0.1700

Data Index: 394634 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8925. Min Act: -0.1700

Data Index: 369071 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8961. Min Act: -0.1700

Data Index: 2310327 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.9186. Min Act: -0.1700

Data Index: 7919806 (Open Web Text)

Max Activating Token Index: 891

Text #15

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8945. Min Act: -0.1700

Data Index: 741334 (Open Web Text)

Max Activating Token Index: 799

Text #16

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8979. Min Act: -0.1700

Data Index: 4532721 (Open Web Text)

Max Activating Token Index: 578

Text #17

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8813. Min Act: -0.1700

Data Index: 7250361 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8772. Min Act: -0.1700

Data Index: 2981294 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 4.0368. Min Range: -4.0368

Max Act: 3.8753. Min Act: -0.1700

Data Index: 7844329 (Open Web Text)

Max Activating Token Index: 826