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

Dataset: Open Web Text

Neuron 368 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: 4.9965. Min Range: -4.9965

Max Act: 4.9965. Min Act: -0.1700

Data Index: 6485918 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9706. Min Act: -0.1700

Data Index: 4829497 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9541. Min Act: -0.1700

Data Index: 5560157 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.9173. Min Act: -0.1700

Data Index: 3878024 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8725. Min Act: -0.1700

Data Index: 5213211 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8714. Min Act: -0.1700

Data Index: 4143303 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8771. Min Act: -0.1700

Data Index: 3508450 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8769. Min Act: -0.1700

Data Index: 7229583 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8869. Min Act: -0.1700

Data Index: 839850 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8883. Min Act: -0.1700

Data Index: 2683126 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8605. Min Act: -0.1700

Data Index: 3059991 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8446. Min Act: -0.1700

Data Index: 1437939 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8558. Min Act: -0.1700

Data Index: 4458163 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8621. Min Act: -0.1700

Data Index: 4317095 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8616. Min Act: -0.1700

Data Index: 5354366 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8481. Min Act: -0.1700

Data Index: 914215 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8404. Min Act: -0.1700

Data Index: 3922992 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8585. Min Act: -0.1700

Data Index: 5655286 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8715. Min Act: -0.1700

Data Index: 6175192 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.9965. Min Range: -4.9965

Max Act: 4.8359. Min Act: -0.1700

Data Index: 2824491 (Open Web Text)

Max Activating Token Index: 7