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

Dataset: Open Web Text

Neuron 876 in Layer 3

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: 3.1551. Min Range: -3.1551

Max Act: 3.1551. Min Act: -0.1700

Data Index: 4475209 (Open Web Text)

Max Activating Token Index: 848

Text #1

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.1332. Min Act: -0.1700

Data Index: 1016681 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0939. Min Act: -0.1700

Data Index: 1377622 (Open Web Text)

Max Activating Token Index: 28

Text #3

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.1069. Min Act: -0.1700

Data Index: 6060401 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0533. Min Act: -0.1700

Data Index: 7187402 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1913541 (Open Web Text)

Max Activating Token Index: 717

Text #6

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0617. Min Act: -0.1700

Data Index: 2879586 (Open Web Text)

Max Activating Token Index: 514

Text #7

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0380. Min Act: -0.1700

Data Index: 7270897 (Open Web Text)

Max Activating Token Index: 189

Text #8

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0216. Min Act: -0.1700

Data Index: 4699540 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0001. Min Act: -0.1700

Data Index: 2506576 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0376. Min Act: -0.1700

Data Index: 2216872 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0248. Min Act: -0.1700

Data Index: 55108 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0326. Min Act: -0.1700

Data Index: 2013509 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.1551. Min Range: -3.1551

Max Act: 2.9945. Min Act: -0.1700

Data Index: 6755779 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 3.1551. Min Range: -3.1551

Max Act: 2.9474. Min Act: -0.1700

Data Index: 7707166 (Open Web Text)

Max Activating Token Index: 772

Text #15

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0384. Min Act: -0.1700

Data Index: 486478 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 3.1551. Min Range: -3.1551

Max Act: 2.9919. Min Act: -0.1700

Data Index: 4809664 (Open Web Text)

Max Activating Token Index: 900

Text #17

Max Range: 3.1551. Min Range: -3.1551

Max Act: 2.9909. Min Act: -0.1700

Data Index: 5838305 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 3.1551. Min Range: -3.1551

Max Act: 3.0041. Min Act: -0.1700

Data Index: 2431654 (Open Web Text)

Max Activating Token Index: 879

Text #19

Max Range: 3.1551. Min Range: -3.1551

Max Act: 2.9979. Min Act: -0.1700

Data Index: 2363598 (Open Web Text)

Max Activating Token Index: 884