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

Dataset: Open Web Text

Neuron 202 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: 1.5197. Min Range: -1.5197

Max Act: 1.5182. Min Act: -0.1700

Data Index: 466924 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.5197. Min Act: -0.1699

Data Index: 4995077 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.5152. Min Act: -0.1700

Data Index: 3876467 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.5060. Min Act: -0.1700

Data Index: 6006591 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.5039. Min Act: -0.1696

Data Index: 7084693 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4984. Min Act: -0.1700

Data Index: 405534 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4958. Min Act: -0.1700

Data Index: 6509155 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4805. Min Act: -0.1700

Data Index: 7439457 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4824. Min Act: -0.1700

Data Index: 4948064 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4747. Min Act: -0.1700

Data Index: 8621148 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4742. Min Act: -0.1700

Data Index: 5300039 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4824. Min Act: -0.1700

Data Index: 7813891 (Open Web Text)

Max Activating Token Index: 59

Text #12

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4723. Min Act: -0.1700

Data Index: 3792086 (Open Web Text)

Max Activating Token Index: 335

Text #13

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4627. Min Act: -0.1683

Data Index: 8304617 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4695. Min Act: -0.1700

Data Index: 7252149 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4634. Min Act: -0.1698

Data Index: 3200741 (Open Web Text)

Max Activating Token Index: 157

Text #16

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4574. Min Act: -0.1700

Data Index: 6434362 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4638. Min Act: -0.1699

Data Index: 6226703 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4587. Min Act: -0.1700

Data Index: 5886368 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 1.5197. Min Range: -1.5197

Max Act: 1.4599. Min Act: -0.1691

Data Index: 911187 (Open Web Text)

Max Activating Token Index: 654