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

Dataset: Open Web Text

Neuron 2595 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: 6.6727. Min Range: -6.6727

Max Act: 6.6727. Min Act: -0.1700

Data Index: 1345013 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5987. Min Act: -0.1700

Data Index: 3148802 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.6118. Min Act: -0.1700

Data Index: 4884862 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5663. Min Act: -0.1700

Data Index: 7229328 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5940. Min Act: -0.1700

Data Index: 3152350 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5921. Min Act: -0.1700

Data Index: 3491370 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5845. Min Act: -0.1700

Data Index: 60294 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5734. Min Act: -0.1700

Data Index: 5327316 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5455. Min Act: -0.1699

Data Index: 6004746 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5490. Min Act: -0.1700

Data Index: 5392003 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5573. Min Act: -0.1700

Data Index: 1500624 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5428. Min Act: -0.1700

Data Index: 4701133 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5462. Min Act: -0.1700

Data Index: 988617 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5327. Min Act: -0.1700

Data Index: 829936 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5414. Min Act: -0.1700

Data Index: 85462 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5302. Min Act: -0.1700

Data Index: 493097 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5287. Min Act: -0.1700

Data Index: 3617563 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5266. Min Act: -0.1700

Data Index: 2733540 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5276. Min Act: -0.1700

Data Index: 1036624 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 6.6727. Min Range: -6.6727

Max Act: 6.5118. Min Act: -0.1700

Data Index: 3388432 (Open Web Text)

Max Activating Token Index: 4