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

Dataset: Open Web Text

Neuron 907 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: 3.2626. Min Range: -3.2626

Max Act: 3.2626. Min Act: -0.1700

Data Index: 1334173 (Open Web Text)

Max Activating Token Index: 599

Text #1

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.2147. Min Act: -0.1700

Data Index: 3606892 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.2222. Min Act: -0.1700

Data Index: 5326978 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.1541. Min Act: -0.1700

Data Index: 4312777 (Open Web Text)

Max Activating Token Index: 964

Text #4

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.1129. Min Act: -0.1700

Data Index: 6960539 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.1146. Min Act: -0.1700

Data Index: 8565406 (Open Web Text)

Max Activating Token Index: 871

Text #6

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0990. Min Act: -0.1700

Data Index: 596239 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.1062. Min Act: -0.1700

Data Index: 3376157 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0499. Min Act: -0.1700

Data Index: 7342654 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0587. Min Act: -0.1700

Data Index: 1902704 (Open Web Text)

Max Activating Token Index: 343

Text #10

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0748. Min Act: -0.1700

Data Index: 8059686 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0630. Min Act: -0.1700

Data Index: 5255549 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0314. Min Act: -0.1700

Data Index: 8352679 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0211. Min Act: -0.1700

Data Index: 7067109 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0207. Min Act: -0.1700

Data Index: 1378575 (Open Web Text)

Max Activating Token Index: 322

Text #15

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0152. Min Act: -0.1700

Data Index: 7926162 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0156. Min Act: -0.1700

Data Index: 3611890 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 3.2626. Min Range: -3.2626

Max Act: 2.9967. Min Act: -0.1700

Data Index: 4070265 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0168. Min Act: -0.1700

Data Index: 3510660 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 3.2626. Min Range: -3.2626

Max Act: 3.0168. Min Act: -0.1700

Data Index: 6702032 (Open Web Text)

Max Activating Token Index: 63