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

Dataset: Open Web Text

Neuron 557 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: 3.6253. Min Range: -3.6253

Max Act: 3.6253. Min Act: -0.1700

Data Index: 985110 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5714. Min Act: -0.1700

Data Index: 359051 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5562. Min Act: -0.1700

Data Index: 921497 (Open Web Text)

Max Activating Token Index: 921

Text #3

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.5799. Min Act: -0.1700

Data Index: 8196297 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4967. Min Act: -0.1700

Data Index: 6631687 (Open Web Text)

Max Activating Token Index: 316

Text #5

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4533. Min Act: -0.1700

Data Index: 8475296 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4397. Min Act: -0.1700

Data Index: 8024042 (Open Web Text)

Max Activating Token Index: 261

Text #7

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4281. Min Act: -0.1700

Data Index: 4047444 (Open Web Text)

Max Activating Token Index: 697

Text #8

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4086. Min Act: -0.1700

Data Index: 7970838 (Open Web Text)

Max Activating Token Index: 852

Text #9

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4150. Min Act: -0.1700

Data Index: 1718167 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.4006. Min Act: -0.1700

Data Index: 4861662 (Open Web Text)

Max Activating Token Index: 287

Text #11

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3987. Min Act: -0.1700

Data Index: 5660934 (Open Web Text)

Max Activating Token Index: 834

Text #12

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3827. Min Act: -0.1700

Data Index: 7330043 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3427. Min Act: -0.1700

Data Index: 5627463 (Open Web Text)

Max Activating Token Index: 284

Text #14

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3621. Min Act: -0.1700

Data Index: 3395337 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3851. Min Act: -0.1700

Data Index: 1512893 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.2993. Min Act: -0.1700

Data Index: 6267772 (Open Web Text)

Max Activating Token Index: 943

Text #17

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3055. Min Act: -0.1700

Data Index: 5591387 (Open Web Text)

Max Activating Token Index: 885

Text #18

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3053. Min Act: -0.1700

Data Index: 6033230 (Open Web Text)

Max Activating Token Index: 252

Text #19

Max Range: 3.6253. Min Range: -3.6253

Max Act: 3.3096. Min Act: -0.1700

Data Index: 7049919 (Open Web Text)

Max Activating Token Index: 560