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

Dataset: Open Web Text

Neuron 2916 in Layer 3

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: 3.8283. Min Range: -3.8283

Max Act: 3.8283. Min Act: -0.1700

Data Index: 6031639 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.7305. Min Act: -0.1700

Data Index: 8481748 (Open Web Text)

Max Activating Token Index: 532

Text #2

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6930. Min Act: -0.1700

Data Index: 5466518 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6939. Min Act: -0.1700

Data Index: 2848536 (Open Web Text)

Max Activating Token Index: 857

Text #4

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6879. Min Act: -0.1700

Data Index: 2544851 (Open Web Text)

Max Activating Token Index: 1012

Text #5

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6954. Min Act: -0.1700

Data Index: 109789 (Open Web Text)

Max Activating Token Index: 225

Text #6

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6577. Min Act: -0.1700

Data Index: 4465263 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6745. Min Act: -0.1700

Data Index: 3925516 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6885. Min Act: -0.1700

Data Index: 6389163 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6549. Min Act: -0.1700

Data Index: 8021293 (Open Web Text)

Max Activating Token Index: 717

Text #10

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6809. Min Act: -0.1700

Data Index: 4758465 (Open Web Text)

Max Activating Token Index: 321

Text #11

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6660. Min Act: -0.1700

Data Index: 2314239 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6549. Min Act: -0.1700

Data Index: 505715 (Open Web Text)

Max Activating Token Index: 822

Text #13

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6450. Min Act: -0.1700

Data Index: 751545 (Open Web Text)

Max Activating Token Index: 728

Text #14

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6604. Min Act: -0.1700

Data Index: 6489387 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6465. Min Act: -0.1700

Data Index: 8533083 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6546. Min Act: -0.1700

Data Index: 5812604 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6373. Min Act: -0.1700

Data Index: 5818304 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6548. Min Act: -0.1700

Data Index: 3490352 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 3.8283. Min Range: -3.8283

Max Act: 3.6447. Min Act: -0.1700

Data Index: 3253882 (Open Web Text)

Max Activating Token Index: 696