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

Dataset: Open Web Text

Neuron 2837 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: 2.6779. Min Range: -2.6779

Max Act: 2.6779. Min Act: -0.1700

Data Index: 7468119 (Open Web Text)

Max Activating Token Index: 758

Text #1

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.6429. Min Act: -0.1700

Data Index: 2063408 (Open Web Text)

Max Activating Token Index: 902

Text #2

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5725. Min Act: -0.1700

Data Index: 763782 (Open Web Text)

Max Activating Token Index: 213

Text #3

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5016. Min Act: -0.1700

Data Index: 8729497 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5370. Min Act: -0.1700

Data Index: 2964308 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5267. Min Act: -0.1700

Data Index: 4034833 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4957. Min Act: -0.1700

Data Index: 4262258 (Open Web Text)

Max Activating Token Index: 224

Text #7

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5175. Min Act: -0.1700

Data Index: 3601655 (Open Web Text)

Max Activating Token Index: 537

Text #8

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4904. Min Act: -0.1700

Data Index: 4710988 (Open Web Text)

Max Activating Token Index: 578

Text #9

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5134. Min Act: -0.1700

Data Index: 4567236 (Open Web Text)

Max Activating Token Index: 940

Text #10

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5059. Min Act: -0.1700

Data Index: 45821 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4797. Min Act: -0.1700

Data Index: 1026179 (Open Web Text)

Max Activating Token Index: 828

Text #12

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4963. Min Act: -0.1700

Data Index: 5757304 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.5067. Min Act: -0.1700

Data Index: 2589022 (Open Web Text)

Max Activating Token Index: 229

Text #14

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4733. Min Act: -0.1700

Data Index: 4265941 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4863. Min Act: -0.1700

Data Index: 5887622 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4828. Min Act: -0.1700

Data Index: 3280789 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4763. Min Act: -0.1700

Data Index: 5772427 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4857. Min Act: -0.1700

Data Index: 4490940 (Open Web Text)

Max Activating Token Index: 883

Text #19

Max Range: 2.6779. Min Range: -2.6779

Max Act: 2.4760. Min Act: -0.1700

Data Index: 1494867 (Open Web Text)

Max Activating Token Index: 82