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

Dataset: Open Web Text

Neuron 755 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: 3.8024. Min Range: -3.8024

Max Act: 3.8024. Min Act: -0.1700

Data Index: 6331480 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6789. Min Act: -0.1700

Data Index: 2111245 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6943. Min Act: -0.1700

Data Index: 2745160 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6154. Min Act: -0.1700

Data Index: 8045569 (Open Web Text)

Max Activating Token Index: 303

Text #4

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6052. Min Act: -0.1700

Data Index: 8267527 (Open Web Text)

Max Activating Token Index: 832

Text #5

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6174. Min Act: -0.1700

Data Index: 3349079 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5674. Min Act: -0.1700

Data Index: 507893 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5798. Min Act: -0.1700

Data Index: 4778278 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6029. Min Act: -0.1700

Data Index: 2944120 (Open Web Text)

Max Activating Token Index: 269

Text #9

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.6103. Min Act: -0.1700

Data Index: 5388374 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5045. Min Act: -0.1700

Data Index: 220455 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5274. Min Act: -0.1700

Data Index: 6923507 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5609. Min Act: -0.1700

Data Index: 3434419 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5848. Min Act: -0.1700

Data Index: 6199474 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5501. Min Act: -0.1700

Data Index: 3698231 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5322. Min Act: -0.1700

Data Index: 391474 (Open Web Text)

Max Activating Token Index: 399

Text #16

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5327. Min Act: -0.1700

Data Index: 274900 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5379. Min Act: -0.1700

Data Index: 2337522 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5535. Min Act: -0.1700

Data Index: 4263097 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 3.8024. Min Range: -3.8024

Max Act: 3.5341. Min Act: -0.1700

Data Index: 423383 (Open Web Text)

Max Activating Token Index: 35