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

Dataset: Open Web Text

Neuron 2921 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: 5.2886. Min Range: -5.2886

Max Act: 5.2886. Min Act: -0.1700

Data Index: 3761329 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.1148. Min Act: -0.1700

Data Index: 5309794 (Open Web Text)

Max Activating Token Index: 862

Text #2

Max Range: 5.2886. Min Range: -5.2886

Max Act: 5.0320. Min Act: -0.1700

Data Index: 7439171 (Open Web Text)

Max Activating Token Index: 784

Text #3

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.9628. Min Act: -0.1700

Data Index: 1944431 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.9705. Min Act: -0.1700

Data Index: 8341257 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.9243. Min Act: -0.1700

Data Index: 5339621 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.9368. Min Act: -0.1700

Data Index: 5913156 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8853. Min Act: -0.1700

Data Index: 4247379 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8997. Min Act: -0.1700

Data Index: 6617756 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8281. Min Act: -0.1700

Data Index: 4984970 (Open Web Text)

Max Activating Token Index: 783

Text #10

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8793. Min Act: -0.1700

Data Index: 7165346 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8557. Min Act: -0.1700

Data Index: 8092147 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8526. Min Act: -0.1700

Data Index: 3025499 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8663. Min Act: -0.1700

Data Index: 5916975 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8043. Min Act: -0.1700

Data Index: 7407590 (Open Web Text)

Max Activating Token Index: 691

Text #15

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.7978. Min Act: -0.1700

Data Index: 8219606 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8183. Min Act: -0.1700

Data Index: 6109094 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.7647. Min Act: -0.1700

Data Index: 3185283 (Open Web Text)

Max Activating Token Index: 287

Text #18

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.7745. Min Act: -0.1700

Data Index: 6930999 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 5.2886. Min Range: -5.2886

Max Act: 4.8124. Min Act: -0.1700

Data Index: 501509 (Open Web Text)

Max Activating Token Index: 424