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

Dataset: Open Web Text

Neuron 1312 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: 5.1072. Min Range: -5.1072

Max Act: 5.1072. Min Act: -0.1700

Data Index: 6534561 (Open Web Text)

Max Activating Token Index: 312

Text #1

Max Range: 5.1072. Min Range: -5.1072

Max Act: 5.0393. Min Act: -0.1700

Data Index: 5654704 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9963. Min Act: -0.1700

Data Index: 6318937 (Open Web Text)

Max Activating Token Index: 790

Text #3

Max Range: 5.1072. Min Range: -5.1072

Max Act: 5.0036. Min Act: -0.1700

Data Index: 1590617 (Open Web Text)

Max Activating Token Index: 557

Text #4

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9526. Min Act: -0.1700

Data Index: 8565317 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9523. Min Act: -0.1700

Data Index: 3824344 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9482. Min Act: -0.1700

Data Index: 7440970 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9408. Min Act: -0.1700

Data Index: 1297036 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9270. Min Act: -0.1700

Data Index: 7444064 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.9165. Min Act: -0.1700

Data Index: 7844040 (Open Web Text)

Max Activating Token Index: 953

Text #10

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8892. Min Act: -0.1700

Data Index: 4540403 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8597. Min Act: -0.1700

Data Index: 1724903 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8811. Min Act: -0.1700

Data Index: 689261 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8642. Min Act: -0.1700

Data Index: 8391339 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8738. Min Act: -0.1700

Data Index: 7070805 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8790. Min Act: -0.1700

Data Index: 4769504 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8746. Min Act: -0.1700

Data Index: 8790345 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8552. Min Act: -0.1700

Data Index: 7142727 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8048. Min Act: -0.1700

Data Index: 2154785 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 5.1072. Min Range: -5.1072

Max Act: 4.8275. Min Act: -0.1700

Data Index: 5878403 (Open Web Text)

Max Activating Token Index: 16