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

Dataset: Open Web Text

Neuron 1608 in Layer 1

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: 4.2668. Min Range: -4.2668

Max Act: 4.2507. Min Act: -0.1700

Data Index: 5938233 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2668. Min Act: -0.1700

Data Index: 7827486 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2512. Min Act: -0.1700

Data Index: 8462409 (Open Web Text)

Max Activating Token Index: 597

Text #3

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2601. Min Act: -0.1700

Data Index: 5386576 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2539. Min Act: -0.1700

Data Index: 1191473 (Open Web Text)

Max Activating Token Index: 689

Text #5

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2294. Min Act: -0.1700

Data Index: 703246 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2290. Min Act: -0.1700

Data Index: 6181459 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2177. Min Act: -0.1700

Data Index: 574823 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2162. Min Act: -0.1700

Data Index: 2956371 (Open Web Text)

Max Activating Token Index: 593

Text #9

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2144. Min Act: -0.1700

Data Index: 4158311 (Open Web Text)

Max Activating Token Index: 226

Text #10

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2112. Min Act: -0.1700

Data Index: 7739946 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2388. Min Act: -0.1700

Data Index: 6306166 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.2173. Min Act: -0.1700

Data Index: 6283576 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1875. Min Act: -0.1700

Data Index: 1292215 (Open Web Text)

Max Activating Token Index: 569

Text #14

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1959. Min Act: -0.1700

Data Index: 2546833 (Open Web Text)

Max Activating Token Index: 297

Text #15

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1867. Min Act: -0.1700

Data Index: 4809039 (Open Web Text)

Max Activating Token Index: 264

Text #16

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1832. Min Act: -0.1700

Data Index: 5206022 (Open Web Text)

Max Activating Token Index: 179

Text #17

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1956. Min Act: -0.1700

Data Index: 3018605 (Open Web Text)

Max Activating Token Index: 571

Text #18

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1879. Min Act: -0.1700

Data Index: 2478907 (Open Web Text)

Max Activating Token Index: 619

Text #19

Max Range: 4.2668. Min Range: -4.2668

Max Act: 4.1932. Min Act: -0.1700

Data Index: 6081535 (Open Web Text)

Max Activating Token Index: 492