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

Dataset: Open Web Text

Neuron 53 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: 3.7964. Min Range: -3.7964

Max Act: 3.7964. Min Act: -0.1700

Data Index: 562786 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.7492. Min Act: -0.1700

Data Index: 1920829 (Open Web Text)

Max Activating Token Index: 791

Text #2

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.7035. Min Act: -0.1700

Data Index: 5216003 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6813. Min Act: -0.1700

Data Index: 1509983 (Open Web Text)

Max Activating Token Index: 990

Text #4

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.7068. Min Act: -0.1700

Data Index: 6552868 (Open Web Text)

Max Activating Token Index: 431

Text #5

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.7063. Min Act: -0.1700

Data Index: 5653801 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6577. Min Act: -0.1700

Data Index: 8434772 (Open Web Text)

Max Activating Token Index: 645

Text #7

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6490. Min Act: -0.1700

Data Index: 1790385 (Open Web Text)

Max Activating Token Index: 42

Text #8

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6441. Min Act: -0.1700

Data Index: 950521 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6233. Min Act: -0.1700

Data Index: 4032349 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1263193 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6190. Min Act: -0.1700

Data Index: 1524610 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5944. Min Act: -0.1700

Data Index: 2325914 (Open Web Text)

Max Activating Token Index: 735

Text #13

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5957. Min Act: -0.1700

Data Index: 2494028 (Open Web Text)

Max Activating Token Index: 1016

Text #14

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6032. Min Act: -0.1700

Data Index: 1762567 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5956. Min Act: -0.1700

Data Index: 442386 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5968. Min Act: -0.1700

Data Index: 8523951 (Open Web Text)

Max Activating Token Index: 338

Text #17

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1754629 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5870. Min Act: -0.1700

Data Index: 8255650 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.6027. Min Act: -0.1700

Data Index: 1998454 (Open Web Text)

Max Activating Token Index: 772