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

Dataset: Open Web Text

Neuron 156 in Layer 2

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: 3.5007. Min Range: -3.5007

Max Act: 3.5007. Min Act: -0.1700

Data Index: 7478834 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.4131. Min Act: -0.1700

Data Index: 7861774 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3886. Min Act: -0.1700

Data Index: 7510776 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3918. Min Act: -0.1700

Data Index: 3290169 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3925. Min Act: -0.1700

Data Index: 7541802 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3872. Min Act: -0.1700

Data Index: 3018186 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.4010. Min Act: -0.1700

Data Index: 7478836 (Open Web Text)

Max Activating Token Index: 645

Text #7

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3704. Min Act: -0.1700

Data Index: 5709421 (Open Web Text)

Max Activating Token Index: 1016

Text #8

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3842. Min Act: -0.1700

Data Index: 61939 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3626. Min Act: -0.1700

Data Index: 6780692 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3444. Min Act: -0.1700

Data Index: 2944569 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3569. Min Act: -0.1700

Data Index: 6264829 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3503. Min Act: -0.1700

Data Index: 4427997 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3559. Min Act: -0.1700

Data Index: 3999088 (Open Web Text)

Max Activating Token Index: 504

Text #14

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3476. Min Act: -0.1700

Data Index: 7503566 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3625. Min Act: -0.1700

Data Index: 8390032 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3682. Min Act: -0.1700

Data Index: 3616632 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3407. Min Act: -0.1700

Data Index: 7118132 (Open Web Text)

Max Activating Token Index: 79

Text #18

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3488. Min Act: -0.1700

Data Index: 7474844 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 3.5007. Min Range: -3.5007

Max Act: 3.3387. Min Act: -0.1700

Data Index: 1299532 (Open Web Text)

Max Activating Token Index: 12