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

Dataset: Open Web Text

Neuron 1805 in Layer 1

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: 1.8534. Min Range: -1.8534

Max Act: 1.8534. Min Act: -0.1700

Data Index: 8482164 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.8296. Min Act: -0.1700

Data Index: 5075567 (Open Web Text)

Max Activating Token Index: 705

Text #2

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.8005. Min Act: -0.1700

Data Index: 1204140 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7763. Min Act: -0.1700

Data Index: 7108143 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7508. Min Act: -0.1700

Data Index: 1204123 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7327. Min Act: -0.1700

Data Index: 4004578 (Open Web Text)

Max Activating Token Index: 615

Text #6

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7096. Min Act: -0.1700

Data Index: 3100211 (Open Web Text)

Max Activating Token Index: 654

Text #7

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7157. Min Act: -0.1700

Data Index: 4589264 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7108. Min Act: -0.1700

Data Index: 5931316 (Open Web Text)

Max Activating Token Index: 394

Text #9

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.7019. Min Act: -0.1700

Data Index: 2815752 (Open Web Text)

Max Activating Token Index: 259

Text #10

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6929. Min Act: -0.1700

Data Index: 7591790 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6971. Min Act: -0.1700

Data Index: 89342 (Open Web Text)

Max Activating Token Index: 672

Text #12

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6931. Min Act: -0.1700

Data Index: 3914595 (Open Web Text)

Max Activating Token Index: 182

Text #13

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6871. Min Act: -0.1700

Data Index: 5168706 (Open Web Text)

Max Activating Token Index: 112

Text #14

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6844. Min Act: -0.1700

Data Index: 7737194 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6833. Min Act: -0.1700

Data Index: 5466357 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6880. Min Act: -0.1700

Data Index: 2413061 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6768. Min Act: -0.1700

Data Index: 2795614 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6815. Min Act: -0.1700

Data Index: 1412016 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.6814. Min Act: -0.1700

Data Index: 4267979 (Open Web Text)

Max Activating Token Index: 590