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

Dataset: Open Web Text

Neuron 1968 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: 3.6146. Min Range: -3.6146

Max Act: 3.6146. Min Act: -0.1700

Data Index: 8030182 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5888. Min Act: -0.1700

Data Index: 7522983 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5612. Min Act: -0.1700

Data Index: 5224265 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5674. Min Act: -0.1700

Data Index: 4027156 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5264. Min Act: -0.1700

Data Index: 5489925 (Open Web Text)

Max Activating Token Index: 691

Text #5

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5036. Min Act: -0.1700

Data Index: 8380999 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5493. Min Act: -0.1700

Data Index: 693600 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5089. Min Act: -0.1700

Data Index: 8562919 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5041. Min Act: -0.1700

Data Index: 14244 (Open Web Text)

Max Activating Token Index: 622

Text #9

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5125. Min Act: -0.1700

Data Index: 336133 (Open Web Text)

Max Activating Token Index: 86

Text #10

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4830. Min Act: -0.1700

Data Index: 8638087 (Open Web Text)

Max Activating Token Index: 816

Text #11

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4569. Min Act: -0.1700

Data Index: 6235073 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4473. Min Act: -0.1700

Data Index: 4156597 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4536. Min Act: -0.1700

Data Index: 4912022 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4820. Min Act: -0.1700

Data Index: 7426920 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4349. Min Act: -0.1700

Data Index: 1218116 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4312. Min Act: -0.1700

Data Index: 248403 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4415. Min Act: -0.1700

Data Index: 7912047 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4471. Min Act: -0.1700

Data Index: 5302605 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4252. Min Act: -0.1700

Data Index: 6979173 (Open Web Text)

Max Activating Token Index: 636