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

Dataset: Open Web Text

Neuron 2105 in Layer 2

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: 3.6999. Min Range: -3.6999

Max Act: 3.6999. Min Act: -0.1700

Data Index: 7015281 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.6157. Min Act: -0.1700

Data Index: 6468973 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5569. Min Act: -0.1700

Data Index: 4534174 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5723. Min Act: -0.1700

Data Index: 5668112 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5622. Min Act: -0.1700

Data Index: 5792115 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5602. Min Act: -0.1700

Data Index: 3353682 (Open Web Text)

Max Activating Token Index: 887

Text #6

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5731. Min Act: -0.1700

Data Index: 607150 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5304. Min Act: -0.1700

Data Index: 486659 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5145. Min Act: -0.1700

Data Index: 3712135 (Open Web Text)

Max Activating Token Index: 155

Text #9

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5473. Min Act: -0.1700

Data Index: 4439283 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5241. Min Act: -0.1700

Data Index: 3927740 (Open Web Text)

Max Activating Token Index: 77

Text #11

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4878. Min Act: -0.1700

Data Index: 4932878 (Open Web Text)

Max Activating Token Index: 852

Text #12

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.5096. Min Act: -0.1700

Data Index: 2638632 (Open Web Text)

Max Activating Token Index: 926

Text #13

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4696. Min Act: -0.1700

Data Index: 2104809 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4956. Min Act: -0.1700

Data Index: 5645385 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4780. Min Act: -0.1700

Data Index: 5657824 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4708. Min Act: -0.1700

Data Index: 3804199 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4772. Min Act: -0.1700

Data Index: 210458 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4710. Min Act: -0.1700

Data Index: 5335150 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 3.6999. Min Range: -3.6999

Max Act: 3.4542. Min Act: -0.1700

Data Index: 414996 (Open Web Text)

Max Activating Token Index: 89