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

Dataset: Open Web Text

Neuron 290 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: 3.2725. Min Range: -3.2725

Max Act: 3.2725. Min Act: -0.1700

Data Index: 2926514 (Open Web Text)

Max Activating Token Index: 252

Text #1

Max Range: 3.2725. Min Range: -3.2725

Max Act: 3.1103. Min Act: -0.1700

Data Index: 7032561 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 3.2725. Min Range: -3.2725

Max Act: 3.0283. Min Act: -0.1700

Data Index: 7304466 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 3.2725. Min Range: -3.2725

Max Act: 3.0228. Min Act: -0.1700

Data Index: 7463858 (Open Web Text)

Max Activating Token Index: 857

Text #4

Max Range: 3.2725. Min Range: -3.2725

Max Act: 3.0184. Min Act: -0.1700

Data Index: 513184 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9932. Min Act: -0.1700

Data Index: 2915693 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9990. Min Act: -0.1700

Data Index: 7260207 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9614. Min Act: -0.1700

Data Index: 8672026 (Open Web Text)

Max Activating Token Index: 642

Text #8

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9611. Min Act: -0.1700

Data Index: 6675873 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9576. Min Act: -0.1700

Data Index: 4511266 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9664. Min Act: -0.1700

Data Index: 3716993 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9675. Min Act: -0.1700

Data Index: 13397 (Open Web Text)

Max Activating Token Index: 755

Text #12

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9338. Min Act: -0.1700

Data Index: 6416354 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9145. Min Act: -0.1700

Data Index: 236820 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9254. Min Act: -0.1700

Data Index: 3994345 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.8853. Min Act: -0.1700

Data Index: 1881449 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.8901. Min Act: -0.1700

Data Index: 5136504 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.8834. Min Act: -0.1700

Data Index: 175109 (Open Web Text)

Max Activating Token Index: 200

Text #18

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.9143. Min Act: -0.1700

Data Index: 3302057 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 3.2725. Min Range: -3.2725

Max Act: 2.8699. Min Act: -0.1700

Data Index: 2528060 (Open Web Text)

Max Activating Token Index: 468