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

Dataset: Open Web Text

Neuron 3015 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: 3.1571. Min Range: -3.1571

Max Act: 3.1571. Min Act: -0.1700

Data Index: 317724 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 3.1571. Min Range: -3.1571

Max Act: 3.0361. Min Act: -0.1700

Data Index: 3591088 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 3.1571. Min Range: -3.1571

Max Act: 3.0049. Min Act: -0.1700

Data Index: 901560 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.9742. Min Act: -0.1700

Data Index: 4233872 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.9834. Min Act: -0.1700

Data Index: 7522546 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.9411. Min Act: -0.1700

Data Index: 8646103 (Open Web Text)

Max Activating Token Index: 346

Text #6

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.9252. Min Act: -0.1700

Data Index: 4878878 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8880. Min Act: -0.1700

Data Index: 7292072 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8710. Min Act: -0.1700

Data Index: 5446970 (Open Web Text)

Max Activating Token Index: 487

Text #9

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8688. Min Act: -0.1700

Data Index: 3445588 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8351. Min Act: -0.1700

Data Index: 7507040 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8160. Min Act: -0.1700

Data Index: 7227 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8110. Min Act: -0.1700

Data Index: 2017397 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8289. Min Act: -0.1700

Data Index: 1114584 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8442. Min Act: -0.1700

Data Index: 4449382 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8050. Min Act: -0.1700

Data Index: 6231245 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.7950. Min Act: -0.1700

Data Index: 6835406 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.7878. Min Act: -0.1700

Data Index: 2368944 (Open Web Text)

Max Activating Token Index: 298

Text #18

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.7979. Min Act: -0.1700

Data Index: 4798589 (Open Web Text)

Max Activating Token Index: 221

Text #19

Max Range: 3.1571. Min Range: -3.1571

Max Act: 2.8146. Min Act: -0.1700

Data Index: 7602601 (Open Web Text)

Max Activating Token Index: 293