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

Dataset: Open Web Text

Neuron 639 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: 3.9195. Min Range: -3.9195

Max Act: 3.9195. Min Act: -0.1700

Data Index: 3758893 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7743. Min Act: -0.1700

Data Index: 6850917 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6986. Min Act: -0.1700

Data Index: 4710660 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7038. Min Act: -0.1700

Data Index: 3241640 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7325. Min Act: -0.1700

Data Index: 2743772 (Open Web Text)

Max Activating Token Index: 529

Text #5

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6969. Min Act: -0.1700

Data Index: 5714327 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6988. Min Act: -0.1700

Data Index: 2215619 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6610. Min Act: -0.1700

Data Index: 2324213 (Open Web Text)

Max Activating Token Index: 689

Text #8

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6775. Min Act: -0.1700

Data Index: 5971682 (Open Web Text)

Max Activating Token Index: 417

Text #9

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6451. Min Act: -0.1700

Data Index: 5872878 (Open Web Text)

Max Activating Token Index: 174

Text #10

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6394. Min Act: -0.1700

Data Index: 5897517 (Open Web Text)

Max Activating Token Index: 261

Text #11

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6479. Min Act: -0.1700

Data Index: 4410861 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6292. Min Act: -0.1700

Data Index: 1508551 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6292. Min Act: -0.1700

Data Index: 6846187 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.5770. Min Act: -0.1700

Data Index: 1437294 (Open Web Text)

Max Activating Token Index: 392

Text #15

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.5961. Min Act: -0.1700

Data Index: 218892 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.5806. Min Act: -0.1700

Data Index: 3522221 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.5713. Min Act: -0.1700

Data Index: 4002162 (Open Web Text)

Max Activating Token Index: 966

Text #18

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.5795. Min Act: -0.1700

Data Index: 110813 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6020. Min Act: -0.1700

Data Index: 4411097 (Open Web Text)

Max Activating Token Index: 499