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

Dataset: Open Web Text

Neuron 1089 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: 4.0148. Min Range: -4.0148

Max Act: 4.0148. Min Act: -0.1700

Data Index: 3332433 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9738. Min Act: -0.1700

Data Index: 210118 (Open Web Text)

Max Activating Token Index: 204

Text #2

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9500. Min Act: -0.1700

Data Index: 2823795 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9131. Min Act: -0.1700

Data Index: 541313 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9451. Min Act: -0.1700

Data Index: 4604218 (Open Web Text)

Max Activating Token Index: 352

Text #5

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9405. Min Act: -0.1700

Data Index: 772455 (Open Web Text)

Max Activating Token Index: 733

Text #6

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8943. Min Act: -0.1700

Data Index: 5455263 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8937. Min Act: -0.1700

Data Index: 7029201 (Open Web Text)

Max Activating Token Index: 673

Text #8

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8901. Min Act: -0.1700

Data Index: 7591225 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8793. Min Act: -0.1700

Data Index: 3927768 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9085. Min Act: -0.1700

Data Index: 7654364 (Open Web Text)

Max Activating Token Index: 758

Text #11

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8807. Min Act: -0.1700

Data Index: 7869097 (Open Web Text)

Max Activating Token Index: 791

Text #12

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8920. Min Act: -0.1700

Data Index: 2294600 (Open Web Text)

Max Activating Token Index: 882

Text #13

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9060. Min Act: -0.1700

Data Index: 7055268 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8859. Min Act: -0.1700

Data Index: 1819794 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.9109. Min Act: -0.1700

Data Index: 8659447 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8625. Min Act: -0.1700

Data Index: 2464776 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8442. Min Act: -0.1700

Data Index: 6421514 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8914. Min Act: -0.1700

Data Index: 6662142 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 4.0148. Min Range: -4.0148

Max Act: 3.8449. Min Act: -0.1700

Data Index: 4560522 (Open Web Text)

Max Activating Token Index: 167