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

Dataset: Open Web Text

Neuron 2206 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: 3.7091. Min Range: -3.7091

Max Act: 3.7091. Min Act: -0.1700

Data Index: 822662 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.4358. Min Act: -0.1700

Data Index: 5021288 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.4203. Min Act: -0.1700

Data Index: 7231724 (Open Web Text)

Max Activating Token Index: 813

Text #3

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3865. Min Act: -0.1700

Data Index: 1160214 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.4070. Min Act: -0.1700

Data Index: 5798552 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3660. Min Act: -0.1700

Data Index: 4044620 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3559. Min Act: -0.1700

Data Index: 1644190 (Open Web Text)

Max Activating Token Index: 251

Text #7

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3220. Min Act: -0.1700

Data Index: 7806614 (Open Web Text)

Max Activating Token Index: 972

Text #8

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3532. Min Act: -0.1700

Data Index: 3069033 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3371. Min Act: -0.1700

Data Index: 6087903 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.3027. Min Act: -0.1700

Data Index: 1105827 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2788. Min Act: -0.1700

Data Index: 2739576 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2649. Min Act: -0.1700

Data Index: 6710265 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2718. Min Act: -0.1700

Data Index: 7543760 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2589. Min Act: -0.1700

Data Index: 37769 (Open Web Text)

Max Activating Token Index: 623

Text #15

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2458. Min Act: -0.1700

Data Index: 6161936 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2423. Min Act: -0.1700

Data Index: 4857417 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2547. Min Act: -0.1700

Data Index: 8450728 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2396. Min Act: -0.1700

Data Index: 1709257 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 3.7091. Min Range: -3.7091

Max Act: 3.2108. Min Act: -0.1700

Data Index: 3377464 (Open Web Text)

Max Activating Token Index: 359