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

Dataset: Open Web Text

Neuron 1603 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: 2.9107. Min Range: -2.9107

Max Act: 2.8946. Min Act: -0.1700

Data Index: 7496325 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8949. Min Act: -0.1700

Data Index: 2545419 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.9107. Min Act: -0.1700

Data Index: 2269866 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8941. Min Act: -0.1700

Data Index: 4271642 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8951. Min Act: -0.1700

Data Index: 2887655 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8897. Min Act: -0.1700

Data Index: 1539982 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8990. Min Act: -0.1700

Data Index: 7078288 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8574. Min Act: -0.1700

Data Index: 3187548 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8535. Min Act: -0.1700

Data Index: 1847188 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8424. Min Act: -0.1700

Data Index: 5760294 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8412. Min Act: -0.1700

Data Index: 6012404 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8156. Min Act: -0.1700

Data Index: 3593013 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8195. Min Act: -0.1700

Data Index: 4488109 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8210. Min Act: -0.1700

Data Index: 6597371 (Open Web Text)

Max Activating Token Index: 135

Text #14

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8054. Min Act: -0.1700

Data Index: 2595387 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8050. Min Act: -0.1700

Data Index: 2225589 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8050. Min Act: -0.1700

Data Index: 6277865 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.7973. Min Act: -0.1700

Data Index: 3601096 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8047. Min Act: -0.1700

Data Index: 1693536 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 2.9107. Min Range: -2.9107

Max Act: 2.8134. Min Act: -0.1700

Data Index: 5247035 (Open Web Text)

Max Activating Token Index: 4