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

Dataset: Open Web Text

Neuron 1316 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: 6.1405. Min Range: -6.1405

Max Act: 6.1405. Min Act: -0.1700

Data Index: 3437970 (Open Web Text)

Max Activating Token Index: 444

Text #1

Max Range: 6.1405. Min Range: -6.1405

Max Act: 6.1093. Min Act: -0.1700

Data Index: 5851623 (Open Web Text)

Max Activating Token Index: 939

Text #2

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9871. Min Act: -0.1700

Data Index: 2627380 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 6.1405. Min Range: -6.1405

Max Act: 6.0249. Min Act: -0.1700

Data Index: 8049945 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9898. Min Act: -0.1700

Data Index: 812339 (Open Web Text)

Max Activating Token Index: 82

Text #5

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9289. Min Act: -0.1700

Data Index: 2551160 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9832. Min Act: -0.1700

Data Index: 1118225 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9752. Min Act: -0.1700

Data Index: 2148225 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9483. Min Act: -0.1700

Data Index: 7046513 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8755. Min Act: -0.1700

Data Index: 6904657 (Open Web Text)

Max Activating Token Index: 580

Text #10

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9024. Min Act: -0.1700

Data Index: 583057 (Open Web Text)

Max Activating Token Index: 879

Text #11

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.9408. Min Act: -0.1700

Data Index: 6828623 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8798. Min Act: -0.1700

Data Index: 2388440 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8481. Min Act: -0.1700

Data Index: 3540384 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8815. Min Act: -0.1700

Data Index: 7706524 (Open Web Text)

Max Activating Token Index: 106

Text #15

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.7695. Min Act: -0.1700

Data Index: 2573622 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8553. Min Act: -0.1699

Data Index: 3775510 (Open Web Text)

Max Activating Token Index: 114

Text #17

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8772. Min Act: -0.1700

Data Index: 1562984 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8643. Min Act: -0.1700

Data Index: 3181694 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 6.1405. Min Range: -6.1405

Max Act: 5.8397. Min Act: -0.1700

Data Index: 3080326 (Open Web Text)

Max Activating Token Index: 79