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

Dataset: Open Web Text

Neuron 347 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: 3.0170. Min Range: -3.0170

Max Act: 3.0069. Min Act: -0.1700

Data Index: 3585870 (Open Web Text)

Max Activating Token Index: 959

Text #1

Max Range: 3.0170. Min Range: -3.0170

Max Act: 3.0170. Min Act: -0.1700

Data Index: 5914926 (Open Web Text)

Max Activating Token Index: 855

Text #2

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.9311. Min Act: -0.1700

Data Index: 5378745 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.9228. Min Act: -0.1700

Data Index: 7673501 (Open Web Text)

Max Activating Token Index: 946

Text #4

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.9246. Min Act: -0.1700

Data Index: 2426836 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8976. Min Act: -0.1700

Data Index: 4395529 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8975. Min Act: -0.1700

Data Index: 1478994 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8700. Min Act: -0.1700

Data Index: 7472246 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8902. Min Act: -0.1700

Data Index: 7472240 (Open Web Text)

Max Activating Token Index: 92

Text #9

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8663. Min Act: -0.1700

Data Index: 2001404 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8776. Min Act: -0.1700

Data Index: 4972411 (Open Web Text)

Max Activating Token Index: 440

Text #11

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8369. Min Act: -0.1700

Data Index: 4941630 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8355. Min Act: -0.1700

Data Index: 7413648 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8667. Min Act: -0.1700

Data Index: 4865174 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8538. Min Act: -0.1700

Data Index: 4097368 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8442. Min Act: -0.1700

Data Index: 5633769 (Open Web Text)

Max Activating Token Index: 378

Text #16

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8649. Min Act: -0.1700

Data Index: 6627862 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8474. Min Act: -0.1700

Data Index: 917305 (Open Web Text)

Max Activating Token Index: 873

Text #18

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8362. Min Act: -0.1700

Data Index: 1824503 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 3.0170. Min Range: -3.0170

Max Act: 2.8404. Min Act: -0.1700

Data Index: 1819629 (Open Web Text)

Max Activating Token Index: 770