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

Dataset: Open Web Text

Neuron 1113 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: 1.5805. Min Range: -1.5805

Max Act: 1.5805. Min Act: -0.1700

Data Index: 8767172 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.5503. Min Act: -0.1700

Data Index: 6049811 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.5065. Min Act: -0.1700

Data Index: 600201 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.5026. Min Act: -0.1700

Data Index: 4602315 (Open Web Text)

Max Activating Token Index: 911

Text #4

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.5059. Min Act: -0.1700

Data Index: 4213240 (Open Web Text)

Max Activating Token Index: 792

Text #5

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.5051. Min Act: -0.1700

Data Index: 1579132 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4900. Min Act: -0.1700

Data Index: 6623949 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4986. Min Act: -0.1700

Data Index: 8616712 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4902. Min Act: -0.1700

Data Index: 6232077 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4865. Min Act: -0.1700

Data Index: 8227064 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4758. Min Act: -0.1700

Data Index: 4582709 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4767. Min Act: -0.1700

Data Index: 4122446 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4805. Min Act: -0.1700

Data Index: 4587374 (Open Web Text)

Max Activating Token Index: 921

Text #13

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4820. Min Act: -0.1700

Data Index: 2846006 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4860. Min Act: -0.1700

Data Index: 8055202 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4750. Min Act: -0.1700

Data Index: 115945 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4762. Min Act: -0.1700

Data Index: 8574047 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4528. Min Act: -0.1700

Data Index: 637103 (Open Web Text)

Max Activating Token Index: 761

Text #18

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4542. Min Act: -0.1700

Data Index: 5216003 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 1.5805. Min Range: -1.5805

Max Act: 1.4647. Min Act: -0.1700

Data Index: 6511101 (Open Web Text)

Max Activating Token Index: 968