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

Dataset: Open Web Text

Neuron 755 in Layer 0

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: 2.9363. Min Range: -2.9363

Max Act: 2.9363. Min Act: -0.1700

Data Index: 6677669 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.9039. Min Act: -0.1700

Data Index: 8182845 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.9122. Min Act: -0.1700

Data Index: 792164 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8861. Min Act: -0.1700

Data Index: 6637447 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8680. Min Act: -0.1700

Data Index: 2210429 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8386. Min Act: -0.1700

Data Index: 1784282 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8359. Min Act: -0.1700

Data Index: 835139 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8354. Min Act: -0.1700

Data Index: 2498428 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8525. Min Act: -0.1700

Data Index: 1377978 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8303. Min Act: -0.1700

Data Index: 563602 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8057. Min Act: -0.1700

Data Index: 1466387 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8099. Min Act: -0.1700

Data Index: 7177882 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8020. Min Act: -0.1700

Data Index: 3193669 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8112. Min Act: -0.1700

Data Index: 4748057 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8147. Min Act: -0.1700

Data Index: 6027373 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8171. Min Act: -0.1700

Data Index: 3793616 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.8112. Min Act: -0.1700

Data Index: 8058127 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.7885. Min Act: -0.1700

Data Index: 6985700 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.7946. Min Act: -0.1700

Data Index: 952478 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.9363. Min Range: -2.9363

Max Act: 2.7950. Min Act: -0.1700

Data Index: 7672428 (Open Web Text)

Max Activating Token Index: 36