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

Dataset: Open Web Text

Neuron 1630 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: 4.8916. Min Range: -4.8916

Max Act: 4.8916. Min Act: -0.1700

Data Index: 6029007 (Open Web Text)

Max Activating Token Index: 939

Text #1

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.8609. Min Act: -0.1700

Data Index: 7625044 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.7681. Min Act: -0.1700

Data Index: 510177 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.7170. Min Act: -0.1700

Data Index: 1977608 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.7280. Min Act: -0.1700

Data Index: 5486998 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.7457. Min Act: -0.1700

Data Index: 262460 (Open Web Text)

Max Activating Token Index: 613

Text #6

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.7162. Min Act: -0.1700

Data Index: 8219212 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.7082. Min Act: -0.1700

Data Index: 7298674 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.6734. Min Act: -0.1700

Data Index: 2980683 (Open Web Text)

Max Activating Token Index: 733

Text #9

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.6621. Min Act: -0.1700

Data Index: 8157145 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.6363. Min Act: -0.1700

Data Index: 3628732 (Open Web Text)

Max Activating Token Index: 948

Text #11

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.6156. Min Act: -0.1700

Data Index: 1743853 (Open Web Text)

Max Activating Token Index: 823

Text #12

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.5786. Min Act: -0.1700

Data Index: 5381845 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.5885. Min Act: -0.1700

Data Index: 7802600 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.5892. Min Act: -0.1700

Data Index: 6034016 (Open Web Text)

Max Activating Token Index: 168

Text #15

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.5824. Min Act: -0.1700

Data Index: 1780174 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.6016. Min Act: -0.1700

Data Index: 5836789 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.5884. Min Act: -0.1700

Data Index: 6694887 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.5974. Min Act: -0.1700

Data Index: 5733445 (Open Web Text)

Max Activating Token Index: 994

Text #19

Max Range: 4.8916. Min Range: -4.8916

Max Act: 4.6091. Min Act: -0.1700

Data Index: 5664263 (Open Web Text)

Max Activating Token Index: 955