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

Dataset: Open Web Text

Neuron 435 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: 4.5595. Min Range: -4.5595

Max Act: 4.5595. Min Act: -0.1700

Data Index: 7047196 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.4544. Min Act: -0.1700

Data Index: 354241 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.4236. Min Act: -0.1700

Data Index: 8795146 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3950. Min Act: -0.1700

Data Index: 5744858 (Open Web Text)

Max Activating Token Index: 873

Text #4

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3756. Min Act: -0.1700

Data Index: 276211 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3420. Min Act: -0.1700

Data Index: 5663995 (Open Web Text)

Max Activating Token Index: 868

Text #6

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3372. Min Act: -0.1700

Data Index: 2876201 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3422. Min Act: -0.1700

Data Index: 5240389 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3380. Min Act: -0.1700

Data Index: 4270518 (Open Web Text)

Max Activating Token Index: 901

Text #9

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3232. Min Act: -0.1700

Data Index: 148957 (Open Web Text)

Max Activating Token Index: 431

Text #10

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3471. Min Act: -0.1700

Data Index: 2030990 (Open Web Text)

Max Activating Token Index: 473

Text #11

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3422. Min Act: -0.1700

Data Index: 1508096 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3244. Min Act: -0.1700

Data Index: 978751 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3328. Min Act: -0.1700

Data Index: 4037995 (Open Web Text)

Max Activating Token Index: 776

Text #14

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3203. Min Act: -0.1700

Data Index: 4040303 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3441. Min Act: -0.1700

Data Index: 3948335 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3134. Min Act: -0.1700

Data Index: 2016925 (Open Web Text)

Max Activating Token Index: 683

Text #17

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.2815. Min Act: -0.1700

Data Index: 1247874 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3314. Min Act: -0.1700

Data Index: 505239 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.5595. Min Range: -4.5595

Max Act: 4.3283. Min Act: -0.1700

Data Index: 2430477 (Open Web Text)

Max Activating Token Index: 761