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

Dataset: Open Web Text

Neuron 91 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: 4.7131. Min Range: -4.7131

Max Act: 4.6938. Min Act: -0.1700

Data Index: 14325 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.6748. Min Act: -0.1700

Data Index: 2993225 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.7131. Min Act: -0.1700

Data Index: 2816258 (Open Web Text)

Max Activating Token Index: 445

Text #3

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.6323. Min Act: -0.1700

Data Index: 923951 (Open Web Text)

Max Activating Token Index: 219

Text #4

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5676. Min Act: -0.1700

Data Index: 2147731 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5743. Min Act: -0.1700

Data Index: 3989683 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5793. Min Act: -0.1700

Data Index: 2127209 (Open Web Text)

Max Activating Token Index: 900

Text #7

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5757. Min Act: -0.1700

Data Index: 2675733 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5664. Min Act: -0.1700

Data Index: 428641 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5398. Min Act: -0.1700

Data Index: 8831055 (Open Web Text)

Max Activating Token Index: 919

Text #10

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5703. Min Act: -0.1700

Data Index: 5277443 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5464. Min Act: -0.1700

Data Index: 3887878 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.5144. Min Act: -0.1700

Data Index: 6551935 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4954. Min Act: -0.1700

Data Index: 7998264 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4947. Min Act: -0.1700

Data Index: 813177 (Open Web Text)

Max Activating Token Index: 851

Text #15

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4738. Min Act: -0.1700

Data Index: 177357 (Open Web Text)

Max Activating Token Index: 804

Text #16

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4721. Min Act: -0.1700

Data Index: 7795941 (Open Web Text)

Max Activating Token Index: 628

Text #17

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4270. Min Act: -0.1700

Data Index: 1733367 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4721. Min Act: -0.1700

Data Index: 5346859 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 4.7131. Min Range: -4.7131

Max Act: 4.4525. Min Act: -0.1700

Data Index: 204252 (Open Web Text)

Max Activating Token Index: 640