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

Dataset: Open Web Text

Neuron 720 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: 5.0481. Min Range: -5.0481

Max Act: 5.0481. Min Act: -0.1700

Data Index: 8544367 (Open Web Text)

Max Activating Token Index: 61

Text #1

Max Range: 5.0481. Min Range: -5.0481

Max Act: 5.0314. Min Act: -0.1700

Data Index: 8671414 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 5.0481. Min Range: -5.0481

Max Act: 5.0030. Min Act: -0.1700

Data Index: 8422359 (Open Web Text)

Max Activating Token Index: 225

Text #3

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.9045. Min Act: -0.1700

Data Index: 6335147 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.8677. Min Act: -0.1700

Data Index: 330787 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.8293. Min Act: -0.1700

Data Index: 7312535 (Open Web Text)

Max Activating Token Index: 597

Text #6

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.8369. Min Act: -0.1700

Data Index: 7283214 (Open Web Text)

Max Activating Token Index: 564

Text #7

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.8052. Min Act: -0.1700

Data Index: 6494136 (Open Web Text)

Max Activating Token Index: 135

Text #8

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7999. Min Act: -0.1700

Data Index: 8276927 (Open Web Text)

Max Activating Token Index: 152

Text #9

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7994. Min Act: -0.1700

Data Index: 3171297 (Open Web Text)

Max Activating Token Index: 243

Text #10

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7889. Min Act: -0.1700

Data Index: 478760 (Open Web Text)

Max Activating Token Index: 682

Text #11

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7931. Min Act: -0.1700

Data Index: 7140770 (Open Web Text)

Max Activating Token Index: 428

Text #12

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7787. Min Act: -0.1700

Data Index: 5051471 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7788. Min Act: -0.1700

Data Index: 7825327 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7809. Min Act: -0.1700

Data Index: 330788 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7708. Min Act: -0.1700

Data Index: 6335157 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7352. Min Act: -0.1700

Data Index: 3283438 (Open Web Text)

Max Activating Token Index: 908

Text #17

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7274. Min Act: -0.1700

Data Index: 1856915 (Open Web Text)

Max Activating Token Index: 847

Text #18

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7597. Min Act: -0.1700

Data Index: 6044193 (Open Web Text)

Max Activating Token Index: 78

Text #19

Max Range: 5.0481. Min Range: -5.0481

Max Act: 4.7346. Min Act: -0.1700

Data Index: 3028765 (Open Web Text)

Max Activating Token Index: 105