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

Dataset: Open Web Text

Neuron 2564 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: 3.0265. Min Range: -3.0265

Max Act: 3.0265. Min Act: -0.1700

Data Index: 8164945 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9655. Min Act: -0.1700

Data Index: 4179741 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9470. Min Act: -0.1700

Data Index: 6752560 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9475. Min Act: -0.1700

Data Index: 2488853 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9483. Min Act: -0.1700

Data Index: 8650654 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9515. Min Act: -0.1700

Data Index: 2290064 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9486. Min Act: -0.1700

Data Index: 2587318 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9421. Min Act: -0.1700

Data Index: 747561 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9268. Min Act: -0.1700

Data Index: 4829095 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9304. Min Act: -0.1700

Data Index: 4174537 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9394. Min Act: -0.1700

Data Index: 2898707 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9169. Min Act: -0.1700

Data Index: 7058475 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9077. Min Act: -0.1700

Data Index: 1233284 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9070. Min Act: -0.1700

Data Index: 809995 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9241. Min Act: -0.1700

Data Index: 3867608 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9107. Min Act: -0.1700

Data Index: 1038159 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.8966. Min Act: -0.1700

Data Index: 768079 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9008. Min Act: -0.1700

Data Index: 2932350 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.9011. Min Act: -0.1700

Data Index: 1805264 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.0265. Min Range: -3.0265

Max Act: 2.8964. Min Act: -0.1700

Data Index: 234451 (Open Web Text)

Max Activating Token Index: 12