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

Dataset: Open Web Text

Neuron 1085 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: 4.0884. Min Range: -4.0884

Max Act: 4.0884. Min Act: -0.1700

Data Index: 702538 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0884. Min Act: -0.1700

Data Index: 6404530 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0884. Min Act: -0.1700

Data Index: 6430981 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0468. Min Act: -0.1700

Data Index: 7797149 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0468. Min Act: -0.1700

Data Index: 7170119 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0468. Min Act: -0.1700

Data Index: 1298479 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0570. Min Act: -0.1700

Data Index: 5346491 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0554. Min Act: -0.1700

Data Index: 4625855 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0884. Min Range: -4.0884

Max Act: 4.0138. Min Act: -0.1700

Data Index: 6243319 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9950. Min Act: -0.1700

Data Index: 7351607 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9948. Min Act: -0.1700

Data Index: 7010221 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 2011450 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9640. Min Act: -0.1700

Data Index: 8809623 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 4386745 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 1931598 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 3952818 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 8258095 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9525. Min Act: -0.1700

Data Index: 6161652 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 3653096 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.0884. Min Range: -4.0884

Max Act: 3.9566. Min Act: -0.1700

Data Index: 287129 (Open Web Text)

Max Activating Token Index: 2