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

Dataset: Open Web Text

Neuron 2905 in Layer 1

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: 3.7202. Min Range: -3.7202

Max Act: 3.7202. Min Act: -0.1700

Data Index: 3309910 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6982. Min Act: -0.1700

Data Index: 3985387 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6924. Min Act: -0.1700

Data Index: 2600430 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6767. Min Act: -0.1694

Data Index: 3062910 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6359. Min Act: -0.1700

Data Index: 2393815 (Open Web Text)

Max Activating Token Index: 49

Text #5

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6202. Min Act: -0.1700

Data Index: 7309132 (Open Web Text)

Max Activating Token Index: 79

Text #6

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6293. Min Act: -0.1700

Data Index: 1928896 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6440. Min Act: -0.1700

Data Index: 6329387 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6432. Min Act: -0.1700

Data Index: 5236369 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6453. Min Act: -0.1700

Data Index: 1533147 (Open Web Text)

Max Activating Token Index: 85

Text #10

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5945. Min Act: -0.1700

Data Index: 626897 (Open Web Text)

Max Activating Token Index: 77

Text #11

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6004. Min Act: -0.1700

Data Index: 6382834 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6184. Min Act: -0.1700

Data Index: 142144 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5914. Min Act: -0.1700

Data Index: 2474970 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5953. Min Act: -0.1700

Data Index: 7444064 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6040. Min Act: -0.1700

Data Index: 8766885 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6042. Min Act: -0.1700

Data Index: 3954765 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6140. Min Act: -0.1700

Data Index: 3597205 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5750. Min Act: -0.1700

Data Index: 3185716 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5628. Min Act: -0.1700

Data Index: 3300757 (Open Web Text)

Max Activating Token Index: 3