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

Dataset: Open Web Text

Neuron 1745 in Layer 5

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: 5.1108. Min Range: -5.1108

Max Act: 5.1108. Min Act: -0.1700

Data Index: 4996186 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8912. Min Act: -0.1700

Data Index: 6922733 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.8176. Min Act: -0.1700

Data Index: 4868400 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.7633. Min Act: -0.1700

Data Index: 8628096 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.7570. Min Act: -0.1700

Data Index: 6520387 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.6443. Min Act: -0.1700

Data Index: 1335540 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.6054. Min Act: -0.1700

Data Index: 4191163 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.6186. Min Act: -0.1700

Data Index: 4773479 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.6045. Min Act: -0.1700

Data Index: 219772 (Open Web Text)

Max Activating Token Index: 758

Text #9

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5930. Min Act: -0.1700

Data Index: 1335528 (Open Web Text)

Max Activating Token Index: 984

Text #10

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5511. Min Act: -0.1700

Data Index: 1480982 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5616. Min Act: -0.1700

Data Index: 2257278 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5328. Min Act: -0.1700

Data Index: 37854 (Open Web Text)

Max Activating Token Index: 880

Text #13

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5497. Min Act: -0.1700

Data Index: 78086 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5287. Min Act: -0.1700

Data Index: 7978057 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5310. Min Act: -0.1700

Data Index: 1634815 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5348. Min Act: -0.1700

Data Index: 2920414 (Open Web Text)

Max Activating Token Index: 634

Text #17

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5146. Min Act: -0.1700

Data Index: 3529138 (Open Web Text)

Max Activating Token Index: 606

Text #18

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.5602. Min Act: -0.1700

Data Index: 1227675 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 5.1108. Min Range: -5.1108

Max Act: 4.4851. Min Act: -0.1700

Data Index: 3889168 (Open Web Text)

Max Activating Token Index: 781