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

Dataset: Open Web Text

Neuron 507 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: 2.6285. Min Range: -2.6285

Max Act: 2.6186. Min Act: -0.1700

Data Index: 3383670 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.6192. Min Act: -0.1700

Data Index: 3562537 (Open Web Text)

Max Activating Token Index: 942

Text #2

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.6251. Min Act: -0.1700

Data Index: 1102244 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.6285. Min Act: -0.1700

Data Index: 4168021 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.6048. Min Act: -0.1700

Data Index: 432092 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5864. Min Act: -0.1700

Data Index: 1077604 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.6032. Min Act: -0.1700

Data Index: 2674835 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5887. Min Act: -0.1700

Data Index: 7079744 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5973. Min Act: -0.1700

Data Index: 4629999 (Open Web Text)

Max Activating Token Index: 198

Text #9

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5802. Min Act: -0.1700

Data Index: 2870177 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5887. Min Act: -0.1700

Data Index: 8409054 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5898. Min Act: -0.1700

Data Index: 169612 (Open Web Text)

Max Activating Token Index: 194

Text #12

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5820. Min Act: -0.1700

Data Index: 7774329 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5752. Min Act: -0.1700

Data Index: 7255360 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5839. Min Act: -0.1700

Data Index: 3712677 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5730. Min Act: -0.1700

Data Index: 374854 (Open Web Text)

Max Activating Token Index: 482

Text #16

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5786. Min Act: -0.1700

Data Index: 878958 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5723. Min Act: -0.1700

Data Index: 6616522 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5762. Min Act: -0.1700

Data Index: 1423451 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 2.6285. Min Range: -2.6285

Max Act: 2.5622. Min Act: -0.1700

Data Index: 3267153 (Open Web Text)

Max Activating Token Index: 451