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

Dataset: Open Web Text

Neuron 1276 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: 2.7108. Min Range: -2.7108

Max Act: 2.7108. Min Act: -0.1700

Data Index: 1336598 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6863. Min Act: -0.1700

Data Index: 5323144 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6757. Min Act: -0.1700

Data Index: 2555467 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6390. Min Act: -0.1700

Data Index: 2555462 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6187. Min Act: -0.1700

Data Index: 2555461 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6377. Min Act: -0.1700

Data Index: 2197429 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6294. Min Act: -0.1700

Data Index: 1588018 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5859. Min Act: -0.1700

Data Index: 7919080 (Open Web Text)

Max Activating Token Index: 844

Text #8

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.6069. Min Act: -0.1700

Data Index: 7940412 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5685. Min Act: -0.1700

Data Index: 385769 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5962. Min Act: -0.1700

Data Index: 5089692 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5795. Min Act: -0.1700

Data Index: 2445890 (Open Web Text)

Max Activating Token Index: 408

Text #12

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5940. Min Act: -0.1700

Data Index: 8177408 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5727. Min Act: -0.1700

Data Index: 2197428 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5593. Min Act: -0.1700

Data Index: 3663557 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5756. Min Act: -0.1700

Data Index: 1018208 (Open Web Text)

Max Activating Token Index: 882

Text #16

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5493. Min Act: -0.1700

Data Index: 776697 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5443. Min Act: -0.1700

Data Index: 3705249 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5861. Min Act: -0.1700

Data Index: 4689637 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.5708. Min Act: -0.1700

Data Index: 3813250 (Open Web Text)

Max Activating Token Index: 124