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

Dataset: Open Web Text

Neuron 505 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: 3.3722. Min Range: -3.3722

Max Act: 3.3722. Min Act: -0.1700

Data Index: 5254282 (Open Web Text)

Max Activating Token Index: 103

Text #1

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3121. Min Act: -0.1700

Data Index: 7489087 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.3179. Min Act: -0.1700

Data Index: 4528023 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2925. Min Act: -0.1700

Data Index: 702180 (Open Web Text)

Max Activating Token Index: 898

Text #4

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2703. Min Act: -0.1700

Data Index: 7383696 (Open Web Text)

Max Activating Token Index: 233

Text #5

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1168889 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2525. Min Act: -0.1700

Data Index: 7264290 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2632. Min Act: -0.1700

Data Index: 1848474 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2465. Min Act: -0.1700

Data Index: 5259513 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2380. Min Act: -0.1700

Data Index: 2581532 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2488. Min Act: -0.1700

Data Index: 1754268 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2261. Min Act: -0.1700

Data Index: 5335671 (Open Web Text)

Max Activating Token Index: 589

Text #12

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2236. Min Act: -0.1700

Data Index: 2121934 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2322. Min Act: -0.1700

Data Index: 6736807 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2283. Min Act: -0.1700

Data Index: 4887842 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2194. Min Act: -0.1700

Data Index: 6474102 (Open Web Text)

Max Activating Token Index: 79

Text #16

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2342. Min Act: -0.1700

Data Index: 5590476 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2077. Min Act: -0.1700

Data Index: 2244059 (Open Web Text)

Max Activating Token Index: 134

Text #18

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2113. Min Act: -0.1700

Data Index: 2907279 (Open Web Text)

Max Activating Token Index: 899

Text #19

Max Range: 3.3722. Min Range: -3.3722

Max Act: 3.2179. Min Act: -0.1700

Data Index: 6811268 (Open Web Text)

Max Activating Token Index: 92