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

Dataset: Open Web Text

Neuron 358 in Layer 2

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: 3.3527. Min Range: -3.3527

Max Act: 3.3527. Min Act: -0.1700

Data Index: 7968212 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.3096. Min Act: -0.1700

Data Index: 1004304 (Open Web Text)

Max Activating Token Index: 258

Text #2

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.3110. Min Act: -0.1700

Data Index: 6997804 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2740. Min Act: -0.1700

Data Index: 132255 (Open Web Text)

Max Activating Token Index: 463

Text #4

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2610. Min Act: -0.1700

Data Index: 5369877 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2523. Min Act: -0.1700

Data Index: 2818021 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2516. Min Act: -0.1700

Data Index: 132254 (Open Web Text)

Max Activating Token Index: 923

Text #7

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2488. Min Act: -0.1700

Data Index: 3519300 (Open Web Text)

Max Activating Token Index: 266

Text #8

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2430. Min Act: -0.1700

Data Index: 7804984 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2458. Min Act: -0.1700

Data Index: 3135908 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2431. Min Act: -0.1700

Data Index: 6619230 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2305. Min Act: -0.1700

Data Index: 2264081 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2389. Min Act: -0.1700

Data Index: 5088593 (Open Web Text)

Max Activating Token Index: 150

Text #13

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2080. Min Act: -0.1700

Data Index: 5549820 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.2092. Min Act: -0.1700

Data Index: 4870898 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1983. Min Act: -0.1700

Data Index: 6727328 (Open Web Text)

Max Activating Token Index: 253

Text #16

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1898. Min Act: -0.1700

Data Index: 1400002 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1850. Min Act: -0.1700

Data Index: 579084 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1709. Min Act: -0.1700

Data Index: 7997453 (Open Web Text)

Max Activating Token Index: 575

Text #19

Max Range: 3.3527. Min Range: -3.3527

Max Act: 3.1904. Min Act: -0.1700

Data Index: 8598367 (Open Web Text)

Max Activating Token Index: 187