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

Dataset: Open Web Text

Neuron 897 in Layer 2

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: 3.7860. Min Range: -3.7860

Max Act: 3.7860. Min Act: -0.1700

Data Index: 6874582 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.7391. Min Act: -0.1700

Data Index: 6874581 (Open Web Text)

Max Activating Token Index: 610

Text #2

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.6240. Min Act: -0.1700

Data Index: 6874579 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.5561. Min Act: -0.1700

Data Index: 699422 (Open Web Text)

Max Activating Token Index: 299

Text #4

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.5018. Min Act: -0.1700

Data Index: 3745272 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.5291. Min Act: -0.1700

Data Index: 5425178 (Open Web Text)

Max Activating Token Index: 268

Text #6

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.5279. Min Act: -0.1700

Data Index: 699421 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4981. Min Act: -0.1700

Data Index: 728606 (Open Web Text)

Max Activating Token Index: 291

Text #8

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4746. Min Act: -0.1700

Data Index: 2974552 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4612. Min Act: -0.1700

Data Index: 2070065 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4821. Min Act: -0.1700

Data Index: 8414600 (Open Web Text)

Max Activating Token Index: 153

Text #11

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.5081. Min Act: -0.1700

Data Index: 1094687 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4855. Min Act: -0.1700

Data Index: 1897635 (Open Web Text)

Max Activating Token Index: 146

Text #13

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4798. Min Act: -0.1700

Data Index: 2104704 (Open Web Text)

Max Activating Token Index: 487

Text #14

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4578. Min Act: -0.1700

Data Index: 2104703 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4353. Min Act: -0.1700

Data Index: 5047170 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4532. Min Act: -0.1700

Data Index: 728597 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4547. Min Act: -0.1700

Data Index: 2974551 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4452. Min Act: -0.1700

Data Index: 699415 (Open Web Text)

Max Activating Token Index: 257

Text #19

Max Range: 3.7860. Min Range: -3.7860

Max Act: 3.4425. Min Act: -0.1700

Data Index: 8310068 (Open Web Text)

Max Activating Token Index: 411