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

Dataset: Open Web Text

Neuron 450 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: 4.6964. Min Range: -4.6964

Max Act: 4.6964. Min Act: -0.1700

Data Index: 8566514 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.6767. Min Act: -0.1700

Data Index: 3040191 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.5176. Min Act: -0.1700

Data Index: 7221534 (Open Web Text)

Max Activating Token Index: 191

Text #3

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4878. Min Act: -0.1700

Data Index: 7131942 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4488. Min Act: -0.1700

Data Index: 3995720 (Open Web Text)

Max Activating Token Index: 758

Text #5

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4602. Min Act: -0.1700

Data Index: 3226296 (Open Web Text)

Max Activating Token Index: 644

Text #6

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4190. Min Act: -0.1700

Data Index: 5733104 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4392. Min Act: -0.1700

Data Index: 22038 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4093. Min Act: -0.1700

Data Index: 2087983 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4105. Min Act: -0.1700

Data Index: 2074628 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3674. Min Act: -0.1700

Data Index: 3159867 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3794. Min Act: -0.1700

Data Index: 3219489 (Open Web Text)

Max Activating Token Index: 508

Text #12

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3901. Min Act: -0.1700

Data Index: 270847 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4032. Min Act: -0.1700

Data Index: 1363990 (Open Web Text)

Max Activating Token Index: 335

Text #14

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.4166. Min Act: -0.1700

Data Index: 3409103 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3592. Min Act: -0.1700

Data Index: 6129087 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3501. Min Act: -0.1700

Data Index: 2242807 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3775. Min Act: -0.1700

Data Index: 1317673 (Open Web Text)

Max Activating Token Index: 634

Text #18

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3694. Min Act: -0.1700

Data Index: 4570632 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.6964. Min Range: -4.6964

Max Act: 4.3593. Min Act: -0.1700

Data Index: 1948814 (Open Web Text)

Max Activating Token Index: 108