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

Dataset: Open Web Text

Neuron 1042 in Layer 5

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: 3.0610. Min Range: -3.0610

Max Act: 3.0453. Min Act: -0.1700

Data Index: 5496245 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 3.0610. Min Range: -3.0610

Max Act: 3.0610. Min Act: -0.1700

Data Index: 6836842 (Open Web Text)

Max Activating Token Index: 833

Text #2

Max Range: 3.0610. Min Range: -3.0610

Max Act: 3.0289. Min Act: -0.1700

Data Index: 2453321 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 3.0610. Min Range: -3.0610

Max Act: 3.0096. Min Act: -0.1700

Data Index: 6448710 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.0610. Min Range: -3.0610

Max Act: 3.0049. Min Act: -0.1700

Data Index: 5069023 (Open Web Text)

Max Activating Token Index: 625

Text #5

Max Range: 3.0610. Min Range: -3.0610

Max Act: 3.0124. Min Act: -0.1700

Data Index: 2912831 (Open Web Text)

Max Activating Token Index: 900

Text #6

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9727. Min Act: -0.1700

Data Index: 2160440 (Open Web Text)

Max Activating Token Index: 697

Text #7

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9706. Min Act: -0.1700

Data Index: 3322642 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9804. Min Act: -0.1700

Data Index: 4161182 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9685. Min Act: -0.1700

Data Index: 6168676 (Open Web Text)

Max Activating Token Index: 885

Text #10

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9626. Min Act: -0.1700

Data Index: 1636251 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9533. Min Act: -0.1700

Data Index: 4608985 (Open Web Text)

Max Activating Token Index: 977

Text #12

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9485. Min Act: -0.1700

Data Index: 2295415 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9738. Min Act: -0.1700

Data Index: 6771193 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9373. Min Act: -0.1700

Data Index: 2371275 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9217. Min Act: -0.1700

Data Index: 489640 (Open Web Text)

Max Activating Token Index: 454

Text #16

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.8991. Min Act: -0.1700

Data Index: 3627322 (Open Web Text)

Max Activating Token Index: 790

Text #17

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9349. Min Act: -0.1700

Data Index: 8594321 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.8997. Min Act: -0.1700

Data Index: 3377139 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 3.0610. Min Range: -3.0610

Max Act: 2.9270. Min Act: -0.1700

Data Index: 2460082 (Open Web Text)

Max Activating Token Index: 600