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

Dataset: Open Web Text

Neuron 2053 in Layer 1

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: 5.2033. Min Range: -5.2033

Max Act: 5.2033. Min Act: -0.1700

Data Index: 2857448 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.1357. Min Act: -0.1700

Data Index: 5081821 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.1039. Min Act: -0.1700

Data Index: 8382533 (Open Web Text)

Max Activating Token Index: 113

Text #3

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0970. Min Act: -0.1700

Data Index: 420102 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.1080. Min Act: -0.1700

Data Index: 1143085 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0755. Min Act: -0.1700

Data Index: 6741263 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0535. Min Act: -0.1700

Data Index: 1214767 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0787. Min Act: -0.1700

Data Index: 3774309 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0560. Min Act: -0.1700

Data Index: 4127402 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0591. Min Act: -0.1700

Data Index: 4899841 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0406. Min Act: -0.1700

Data Index: 5386964 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0340. Min Act: -0.1700

Data Index: 1062087 (Open Web Text)

Max Activating Token Index: 986

Text #12

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0271. Min Act: -0.1700

Data Index: 4401107 (Open Web Text)

Max Activating Token Index: 333

Text #13

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0198. Min Act: -0.1700

Data Index: 4248367 (Open Web Text)

Max Activating Token Index: 374

Text #14

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0398. Min Act: -0.1700

Data Index: 2629791 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0294. Min Act: -0.1700

Data Index: 817220 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0201. Min Act: -0.1700

Data Index: 4160184 (Open Web Text)

Max Activating Token Index: 353

Text #17

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0232. Min Act: -0.1700

Data Index: 2134469 (Open Web Text)

Max Activating Token Index: 579

Text #18

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0376. Min Act: -0.1700

Data Index: 3476556 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 5.2033. Min Range: -5.2033

Max Act: 5.0434. Min Act: -0.1700

Data Index: 2952758 (Open Web Text)

Max Activating Token Index: 82