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

Dataset: Open Web Text

Neuron 650 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: 3.7127. Min Range: -3.7127

Max Act: 3.7127. Min Act: -0.1700

Data Index: 4370282 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6507. Min Act: -0.1700

Data Index: 3094466 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6038. Min Act: -0.1700

Data Index: 1967119 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6174. Min Act: -0.1700

Data Index: 7090544 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5749. Min Act: -0.1700

Data Index: 4123060 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5776. Min Act: -0.1700

Data Index: 2758118 (Open Web Text)

Max Activating Token Index: 853

Text #6

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5881. Min Act: -0.1700

Data Index: 3735081 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5617. Min Act: -0.1700

Data Index: 3923388 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5461. Min Act: -0.1700

Data Index: 669830 (Open Web Text)

Max Activating Token Index: 925

Text #9

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5351. Min Act: -0.1700

Data Index: 3194591 (Open Web Text)

Max Activating Token Index: 605

Text #10

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5937. Min Act: -0.1700

Data Index: 5377244 (Open Web Text)

Max Activating Token Index: 944

Text #11

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5827. Min Act: -0.1700

Data Index: 6731547 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5618. Min Act: -0.1700

Data Index: 7462093 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5390. Min Act: -0.1700

Data Index: 3988866 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5307. Min Act: -0.1700

Data Index: 33317 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5227. Min Act: -0.1700

Data Index: 2213744 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5425. Min Act: -0.1700

Data Index: 3871367 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5476. Min Act: -0.1700

Data Index: 2276181 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.5356. Min Act: -0.1700

Data Index: 6009252 (Open Web Text)

Max Activating Token Index: 931

Text #19

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.4938. Min Act: -0.1700

Data Index: 2994120 (Open Web Text)

Max Activating Token Index: 97