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

Dataset: Open Web Text

Neuron 690 in Layer 4

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: 4.4999. Min Range: -4.4999

Max Act: 4.4999. Min Act: -0.1700

Data Index: 6265944 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.4704. Min Act: -0.1700

Data Index: 6556325 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.4101. Min Act: -0.1700

Data Index: 895724 (Open Web Text)

Max Activating Token Index: 878

Text #3

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.4180. Min Act: -0.1700

Data Index: 7935837 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.4024. Min Act: -0.1700

Data Index: 2195303 (Open Web Text)

Max Activating Token Index: 159

Text #5

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3400. Min Act: -0.1700

Data Index: 1214875 (Open Web Text)

Max Activating Token Index: 883

Text #6

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3637. Min Act: -0.1700

Data Index: 544320 (Open Web Text)

Max Activating Token Index: 959

Text #7

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3522. Min Act: -0.1700

Data Index: 2969002 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3633. Min Act: -0.1700

Data Index: 1307960 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3360. Min Act: -0.1700

Data Index: 2090492 (Open Web Text)

Max Activating Token Index: 80

Text #10

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3546. Min Act: -0.1700

Data Index: 4923977 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3571. Min Act: -0.1700

Data Index: 355235 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3154. Min Act: -0.1700

Data Index: 2071312 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3364. Min Act: -0.1700

Data Index: 8553540 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3470. Min Act: -0.1700

Data Index: 4541611 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3289. Min Act: -0.1700

Data Index: 2177773 (Open Web Text)

Max Activating Token Index: 168

Text #16

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3425. Min Act: -0.1700

Data Index: 1534007 (Open Web Text)

Max Activating Token Index: 394

Text #17

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3143. Min Act: -0.1700

Data Index: 5900057 (Open Web Text)

Max Activating Token Index: 990

Text #18

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.3108. Min Act: -0.1700

Data Index: 528809 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 4.4999. Min Range: -4.4999

Max Act: 4.2883. Min Act: -0.1700

Data Index: 3793263 (Open Web Text)

Max Activating Token Index: 151