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

Dataset: Open Web Text

Neuron 3050 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: 3.0367. Min Range: -3.0367

Max Act: 3.0367. Min Act: -0.1700

Data Index: 5362987 (Open Web Text)

Max Activating Token Index: 141

Text #1

Max Range: 3.0367. Min Range: -3.0367

Max Act: 3.0020. Min Act: -0.1700

Data Index: 3546652 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9594. Min Act: -0.1700

Data Index: 1459797 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9322. Min Act: -0.1700

Data Index: 5006817 (Open Web Text)

Max Activating Token Index: 128

Text #4

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9015. Min Act: -0.1700

Data Index: 7614525 (Open Web Text)

Max Activating Token Index: 551

Text #5

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.9070. Min Act: -0.1700

Data Index: 1680228 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8940. Min Act: -0.1700

Data Index: 3567303 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8876. Min Act: -0.1700

Data Index: 7252881 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8856. Min Act: -0.1700

Data Index: 985054 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8416. Min Act: -0.1700

Data Index: 716693 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8335. Min Act: -0.1700

Data Index: 1949002 (Open Web Text)

Max Activating Token Index: 388

Text #11

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8000. Min Act: -0.1700

Data Index: 6864610 (Open Web Text)

Max Activating Token Index: 250

Text #12

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7733. Min Act: -0.1700

Data Index: 3606557 (Open Web Text)

Max Activating Token Index: 432

Text #13

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.8069. Min Act: -0.1700

Data Index: 7805045 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7829. Min Act: -0.1700

Data Index: 3874948 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7824. Min Act: -0.1700

Data Index: 660942 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7328. Min Act: -0.1700

Data Index: 4007583 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7565. Min Act: -0.1700

Data Index: 7323796 (Open Web Text)

Max Activating Token Index: 884

Text #18

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7618. Min Act: -0.1700

Data Index: 2448005 (Open Web Text)

Max Activating Token Index: 110

Text #19

Max Range: 3.0367. Min Range: -3.0367

Max Act: 2.7267. Min Act: -0.1700

Data Index: 5674450 (Open Web Text)

Max Activating Token Index: 589