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

Dataset: Open Web Text

Neuron 497 in Layer 6

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: 5.6081. Min Range: -5.6081

Max Act: 5.6081. Min Act: -0.1700

Data Index: 2929942 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 5.6081. Min Range: -5.6081

Max Act: 5.2761. Min Act: -0.1700

Data Index: 3124241 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.8822. Min Act: -0.1700

Data Index: 5815229 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.8673. Min Act: -0.1700

Data Index: 6833305 (Open Web Text)

Max Activating Token Index: 846

Text #4

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.8924. Min Act: -0.1700

Data Index: 1979515 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.8535. Min Act: -0.1700

Data Index: 5494911 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.8245. Min Act: -0.1700

Data Index: 7809307 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7818. Min Act: -0.1700

Data Index: 3595022 (Open Web Text)

Max Activating Token Index: 179

Text #8

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7237. Min Act: -0.1700

Data Index: 3317206 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7784. Min Act: -0.1700

Data Index: 684413 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7445. Min Act: -0.1700

Data Index: 3028007 (Open Web Text)

Max Activating Token Index: 722

Text #11

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7072. Min Act: -0.1700

Data Index: 2568103 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7084. Min Act: -0.1700

Data Index: 501214 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7180. Min Act: -0.1700

Data Index: 4056549 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7231. Min Act: -0.1700

Data Index: 3834411 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.7138. Min Act: -0.1700

Data Index: 1221677 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.6317. Min Act: -0.1700

Data Index: 1685236 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.6804. Min Act: -0.1700

Data Index: 432912 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.6406. Min Act: -0.1700

Data Index: 7923657 (Open Web Text)

Max Activating Token Index: 383

Text #19

Max Range: 5.6081. Min Range: -5.6081

Max Act: 4.6129. Min Act: -0.1700

Data Index: 2232407 (Open Web Text)

Max Activating Token Index: 871