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

Dataset: Open Web Text

Neuron 876 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: 5.1932. Min Range: -5.1932

Max Act: 5.1932. Min Act: -0.1700

Data Index: 2166961 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.1671. Min Act: -0.1700

Data Index: 7782838 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.1367. Min Act: -0.1700

Data Index: 2894223 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0607. Min Act: -0.1700

Data Index: 3515754 (Open Web Text)

Max Activating Token Index: 618

Text #4

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0825. Min Act: -0.1700

Data Index: 709921 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0938. Min Act: -0.1700

Data Index: 6574901 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0793. Min Act: -0.1700

Data Index: 8112964 (Open Web Text)

Max Activating Token Index: 769

Text #7

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0367. Min Act: -0.1700

Data Index: 7262520 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0075. Min Act: -0.1700

Data Index: 4997667 (Open Web Text)

Max Activating Token Index: 727

Text #9

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0458. Min Act: -0.1700

Data Index: 2714881 (Open Web Text)

Max Activating Token Index: 553

Text #10

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0264. Min Act: -0.1700

Data Index: 8208718 (Open Web Text)

Max Activating Token Index: 760

Text #11

Max Range: 5.1932. Min Range: -5.1932

Max Act: 4.9970. Min Act: -0.1700

Data Index: 4575590 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0118. Min Act: -0.1700

Data Index: 2824977 (Open Web Text)

Max Activating Token Index: 967

Text #13

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0110. Min Act: -0.1700

Data Index: 3965297 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0003. Min Act: -0.1700

Data Index: 7731453 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0098. Min Act: -0.1700

Data Index: 4203562 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 5.1932. Min Range: -5.1932

Max Act: 4.9920. Min Act: -0.1700

Data Index: 2388458 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 5.1932. Min Range: -5.1932

Max Act: 4.9628. Min Act: -0.1700

Data Index: 2485838 (Open Web Text)

Max Activating Token Index: 127

Text #18

Max Range: 5.1932. Min Range: -5.1932

Max Act: 5.0020. Min Act: -0.1700

Data Index: 374323 (Open Web Text)

Max Activating Token Index: 623

Text #19

Max Range: 5.1932. Min Range: -5.1932

Max Act: 4.9722. Min Act: -0.1700

Data Index: 733227 (Open Web Text)

Max Activating Token Index: 371