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

Dataset: Open Web Text

Neuron 2172 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: 7.0512. Min Range: -7.0512

Max Act: 7.0512. Min Act: -0.1700

Data Index: 2895301 (Open Web Text)

Max Activating Token Index: 781

Text #1

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.8077. Min Act: -0.1700

Data Index: 965836 (Open Web Text)

Max Activating Token Index: 748

Text #2

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.8059. Min Act: -0.1700

Data Index: 5010717 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.8800. Min Act: -0.1700

Data Index: 4049274 (Open Web Text)

Max Activating Token Index: 785

Text #4

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.7708. Min Act: -0.1699

Data Index: 8749149 (Open Web Text)

Max Activating Token Index: 760

Text #5

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.7508. Min Act: -0.1700

Data Index: 2870643 (Open Web Text)

Max Activating Token Index: 681

Text #6

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.6717. Min Act: -0.1700

Data Index: 3979953 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.7121. Min Act: -0.1700

Data Index: 4727786 (Open Web Text)

Max Activating Token Index: 392

Text #8

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.6929. Min Act: -0.1700

Data Index: 908121 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.7017. Min Act: -0.1700

Data Index: 4777026 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.6592. Min Act: -0.1700

Data Index: 5302602 (Open Web Text)

Max Activating Token Index: 958

Text #11

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.6484. Min Act: -0.1700

Data Index: 4984538 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.6293. Min Act: -0.1700

Data Index: 3856525 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5927. Min Act: -0.1700

Data Index: 292830 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5924. Min Act: -0.1700

Data Index: 272978 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5750. Min Act: -0.1698

Data Index: 8182534 (Open Web Text)

Max Activating Token Index: 1013

Text #16

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5671. Min Act: -0.1700

Data Index: 985538 (Open Web Text)

Max Activating Token Index: 201

Text #17

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5690. Min Act: -0.1700

Data Index: 8588999 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5741. Min Act: -0.1700

Data Index: 1068644 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 7.0512. Min Range: -7.0512

Max Act: 6.5747. Min Act: -0.1700

Data Index: 7337176 (Open Web Text)

Max Activating Token Index: 427