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

Dataset: Open Web Text

Neuron 1355 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: 3.3758. Min Range: -3.3758

Max Act: 3.3758. Min Act: -0.1700

Data Index: 313536 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.3395. Min Act: -0.1700

Data Index: 4737371 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2921. Min Act: -0.1700

Data Index: 4876125 (Open Web Text)

Max Activating Token Index: 516

Text #3

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2531. Min Act: -0.1700

Data Index: 6567756 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2163. Min Act: -0.1700

Data Index: 2139146 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2343. Min Act: -0.1700

Data Index: 525799 (Open Web Text)

Max Activating Token Index: 206

Text #6

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2364. Min Act: -0.1700

Data Index: 5570869 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2032. Min Act: -0.1700

Data Index: 6628403 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2170. Min Act: -0.1700

Data Index: 4479976 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1894. Min Act: -0.1700

Data Index: 2950324 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1947. Min Act: -0.1700

Data Index: 4424822 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2158. Min Act: -0.1700

Data Index: 462118 (Open Web Text)

Max Activating Token Index: 489

Text #12

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1762. Min Act: -0.1700

Data Index: 8733949 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1721. Min Act: -0.1700

Data Index: 5403724 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1500. Min Act: -0.1700

Data Index: 4701830 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1505. Min Act: -0.1700

Data Index: 6021214 (Open Web Text)

Max Activating Token Index: 732

Text #16

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1629. Min Act: -0.1700

Data Index: 1983417 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1643. Min Act: -0.1700

Data Index: 5505074 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1421. Min Act: -0.1700

Data Index: 3408575 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1736. Min Act: -0.1700

Data Index: 778768 (Open Web Text)

Max Activating Token Index: 414