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

Dataset: Open Web Text

Neuron 2576 in Layer 6

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: 5.1041. Min Range: -5.1041

Max Act: 5.1041. Min Act: -0.1700

Data Index: 2387741 (Open Web Text)

Max Activating Token Index: 286

Text #1

Max Range: 5.1041. Min Range: -5.1041

Max Act: 5.0490. Min Act: -0.1700

Data Index: 1092900 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 5.1041. Min Range: -5.1041

Max Act: 5.0211. Min Act: -0.1700

Data Index: 2584586 (Open Web Text)

Max Activating Token Index: 102

Text #3

Max Range: 5.1041. Min Range: -5.1041

Max Act: 5.0003. Min Act: -0.1700

Data Index: 8486245 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9847. Min Act: -0.1700

Data Index: 4553128 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9827. Min Act: -0.1700

Data Index: 6525986 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9531. Min Act: -0.1700

Data Index: 1644448 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9883. Min Act: -0.1700

Data Index: 8440057 (Open Web Text)

Max Activating Token Index: 385

Text #8

Max Range: 5.1041. Min Range: -5.1041

Max Act: 5.0089. Min Act: -0.1700

Data Index: 916199 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9882. Min Act: -0.1700

Data Index: 1524816 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9730. Min Act: -0.1700

Data Index: 1753736 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9228. Min Act: -0.1700

Data Index: 6683647 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9230. Min Act: -0.1700

Data Index: 3867472 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9380. Min Act: -0.1700

Data Index: 4835159 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.8872. Min Act: -0.1700

Data Index: 6418300 (Open Web Text)

Max Activating Token Index: 609

Text #15

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.8924. Min Act: -0.1700

Data Index: 3046605 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9158. Min Act: -0.1700

Data Index: 6515610 (Open Web Text)

Max Activating Token Index: 497

Text #17

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9284. Min Act: -0.1700

Data Index: 7900308 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.9082. Min Act: -0.1700

Data Index: 6555462 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 5.1041. Min Range: -5.1041

Max Act: 4.8690. Min Act: -0.1700

Data Index: 4613398 (Open Web Text)

Max Activating Token Index: 393