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

Dataset: Open Web Text

Neuron 248 in Layer 3

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: 4.1538. Min Range: -4.1538

Max Act: 4.1538. Min Act: -0.1700

Data Index: 1159286 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.1079. Min Act: -0.1700

Data Index: 2895624 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0984. Min Act: -0.1700

Data Index: 4863085 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0821. Min Act: -0.1700

Data Index: 7808575 (Open Web Text)

Max Activating Token Index: 632

Text #4

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0695. Min Act: -0.1700

Data Index: 4013865 (Open Web Text)

Max Activating Token Index: 786

Text #5

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0587. Min Act: -0.1700

Data Index: 5282027 (Open Web Text)

Max Activating Token Index: 759

Text #6

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0164. Min Act: -0.1700

Data Index: 8739357 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0303. Min Act: -0.1700

Data Index: 1744922 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0158. Min Act: -0.1700

Data Index: 2295035 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0203. Min Act: -0.1700

Data Index: 1188781 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0171. Min Act: -0.1700

Data Index: 6432898 (Open Web Text)

Max Activating Token Index: 712

Text #11

Max Range: 4.1538. Min Range: -4.1538

Max Act: 3.9919. Min Act: -0.1700

Data Index: 8402441 (Open Web Text)

Max Activating Token Index: 736

Text #12

Max Range: 4.1538. Min Range: -4.1538

Max Act: 3.9987. Min Act: -0.1700

Data Index: 8130366 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0106. Min Act: -0.1700

Data Index: 7753216 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0048. Min Act: -0.1700

Data Index: 7440996 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 4.1538. Min Range: -4.1538

Max Act: 3.9760. Min Act: -0.1700

Data Index: 3622932 (Open Web Text)

Max Activating Token Index: 547

Text #16

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0010. Min Act: -0.1700

Data Index: 4663881 (Open Web Text)

Max Activating Token Index: 755

Text #17

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0209. Min Act: -0.1700

Data Index: 3492115 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0205. Min Act: -0.1700

Data Index: 73201 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 4.1538. Min Range: -4.1538

Max Act: 4.0167. Min Act: -0.1700

Data Index: 3224273 (Open Web Text)

Max Activating Token Index: 772