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

Dataset: Open Web Text

Neuron 1479 in Layer 6

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: 6.0910. Min Range: -6.0910

Max Act: 6.0910. Min Act: -0.1700

Data Index: 6719386 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 6.0910. Min Range: -6.0910

Max Act: 6.0358. Min Act: -0.1700

Data Index: 3657981 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.9836. Min Act: -0.1700

Data Index: 1994759 (Open Web Text)

Max Activating Token Index: 346

Text #3

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.9930. Min Act: -0.1700

Data Index: 1114929 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8810. Min Act: -0.1700

Data Index: 5820275 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8915. Min Act: -0.1700

Data Index: 6540726 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8354. Min Act: -0.1700

Data Index: 6461422 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8428. Min Act: -0.1700

Data Index: 6916227 (Open Web Text)

Max Activating Token Index: 847

Text #8

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8035. Min Act: -0.1700

Data Index: 795278 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8048. Min Act: -0.1700

Data Index: 3662474 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8325. Min Act: -0.1700

Data Index: 7347832 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.8424. Min Act: -0.1700

Data Index: 4183467 (Open Web Text)

Max Activating Token Index: 794

Text #12

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7772. Min Act: -0.1700

Data Index: 7409003 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7891. Min Act: -0.1700

Data Index: 847813 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7583. Min Act: -0.1700

Data Index: 2398848 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7828. Min Act: -0.1700

Data Index: 2714746 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7677. Min Act: -0.1700

Data Index: 5203543 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7568. Min Act: -0.1700

Data Index: 8087057 (Open Web Text)

Max Activating Token Index: 984

Text #18

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7125. Min Act: -0.1700

Data Index: 2445263 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 6.0910. Min Range: -6.0910

Max Act: 5.7432. Min Act: -0.1700

Data Index: 3271895 (Open Web Text)

Max Activating Token Index: 354