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

Dataset: Open Web Text

Neuron 427 in Layer 5

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: 4.8855. Min Range: -4.8855

Max Act: 4.8855. Min Act: -0.1700

Data Index: 4946691 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.8122. Min Act: -0.1700

Data Index: 3549488 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.7934. Min Act: -0.1700

Data Index: 7752064 (Open Web Text)

Max Activating Token Index: 392

Text #3

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.7425. Min Act: -0.1700

Data Index: 1494775 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.7243. Min Act: -0.1700

Data Index: 7148652 (Open Web Text)

Max Activating Token Index: 693

Text #5

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.7188. Min Act: -0.1700

Data Index: 2280650 (Open Web Text)

Max Activating Token Index: 428

Text #6

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6747. Min Act: -0.1700

Data Index: 3658437 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6392. Min Act: -0.1700

Data Index: 288488 (Open Web Text)

Max Activating Token Index: 388

Text #8

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6537. Min Act: -0.1700

Data Index: 6425685 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6491. Min Act: -0.1700

Data Index: 3348417 (Open Web Text)

Max Activating Token Index: 402

Text #10

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6639. Min Act: -0.1700

Data Index: 2005159 (Open Web Text)

Max Activating Token Index: 158

Text #11

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6607. Min Act: -0.1700

Data Index: 2453874 (Open Web Text)

Max Activating Token Index: 895

Text #12

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6499. Min Act: -0.1700

Data Index: 3843260 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6287. Min Act: -0.1700

Data Index: 5803526 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6379. Min Act: -0.1700

Data Index: 650151 (Open Web Text)

Max Activating Token Index: 871

Text #15

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6272. Min Act: -0.1700

Data Index: 6261726 (Open Web Text)

Max Activating Token Index: 647

Text #16

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6302. Min Act: -0.1700

Data Index: 2031347 (Open Web Text)

Max Activating Token Index: 176

Text #17

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6444. Min Act: -0.1700

Data Index: 3533607 (Open Web Text)

Max Activating Token Index: 808

Text #18

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6444. Min Act: -0.1700

Data Index: 3732763 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 4.8855. Min Range: -4.8855

Max Act: 4.6437. Min Act: -0.1700

Data Index: 775161 (Open Web Text)

Max Activating Token Index: 975