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

Dataset: Open Web Text

Neuron 2695 in Layer 4

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: 3.0881. Min Range: -3.0881

Max Act: 3.0881. Min Act: -0.1700

Data Index: 157516 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9394. Min Act: -0.1700

Data Index: 6238718 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9619. Min Act: -0.1700

Data Index: 5210754 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9387. Min Act: -0.1700

Data Index: 6418551 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9294. Min Act: -0.1700

Data Index: 1112656 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.9031. Min Act: -0.1700

Data Index: 814826 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8882. Min Act: -0.1700

Data Index: 781723 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8828. Min Act: -0.1700

Data Index: 5803531 (Open Web Text)

Max Activating Token Index: 993

Text #8

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8779. Min Act: -0.1700

Data Index: 4213872 (Open Web Text)

Max Activating Token Index: 700

Text #9

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8741. Min Act: -0.1700

Data Index: 4943342 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8879. Min Act: -0.1700

Data Index: 2399458 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8294. Min Act: -0.1700

Data Index: 6931102 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8557. Min Act: -0.1700

Data Index: 2487591 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8580. Min Act: -0.1700

Data Index: 6560504 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8337. Min Act: -0.1700

Data Index: 4243502 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8070. Min Act: -0.1700

Data Index: 8350040 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8311. Min Act: -0.1700

Data Index: 2284178 (Open Web Text)

Max Activating Token Index: 976

Text #17

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8385. Min Act: -0.1700

Data Index: 4326895 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8247. Min Act: -0.1700

Data Index: 1681190 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.0881. Min Range: -3.0881

Max Act: 2.8292. Min Act: -0.1700

Data Index: 6510112 (Open Web Text)

Max Activating Token Index: 109