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

Dataset: Open Web Text

Neuron 1801 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: 6.4209. Min Range: -6.4209

Max Act: 6.4209. Min Act: -0.1700

Data Index: 2800471 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.4005. Min Act: -0.1700

Data Index: 6422643 (Open Web Text)

Max Activating Token Index: 148

Text #2

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.3743. Min Act: -0.1700

Data Index: 1111355 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.3917. Min Act: -0.1700

Data Index: 7288122 (Open Web Text)

Max Activating Token Index: 524

Text #4

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.3382. Min Act: -0.1700

Data Index: 2144807 (Open Web Text)

Max Activating Token Index: 937

Text #5

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.3004. Min Act: -0.1700

Data Index: 3637006 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2929. Min Act: -0.1700

Data Index: 3068376 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2976. Min Act: -0.1700

Data Index: 693794 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2906. Min Act: -0.1700

Data Index: 4670164 (Open Web Text)

Max Activating Token Index: 195

Text #9

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2840. Min Act: -0.1700

Data Index: 8807018 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2677. Min Act: -0.1700

Data Index: 7151922 (Open Web Text)

Max Activating Token Index: 520

Text #11

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2076. Min Act: -0.1700

Data Index: 93455 (Open Web Text)

Max Activating Token Index: 322

Text #12

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2023. Min Act: -0.1700

Data Index: 3993664 (Open Web Text)

Max Activating Token Index: 671

Text #13

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.1667. Min Act: -0.1700

Data Index: 76717 (Open Web Text)

Max Activating Token Index: 260

Text #14

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.2032. Min Act: -0.1700

Data Index: 2832171 (Open Web Text)

Max Activating Token Index: 464

Text #15

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.1523. Min Act: -0.1700

Data Index: 8009122 (Open Web Text)

Max Activating Token Index: 331

Text #16

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.1368. Min Act: -0.1700

Data Index: 4586299 (Open Web Text)

Max Activating Token Index: 952

Text #17

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.0909. Min Act: -0.1700

Data Index: 871499 (Open Web Text)

Max Activating Token Index: 188

Text #18

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.0736. Min Act: -0.1700

Data Index: 5343078 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 6.4209. Min Range: -6.4209

Max Act: 6.0862. Min Act: -0.1700

Data Index: 6880069 (Open Web Text)

Max Activating Token Index: 352