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

Dataset: Open Web Text

Neuron 506 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: 4.5064. Min Range: -4.5064

Max Act: 4.5064. Min Act: -0.1700

Data Index: 3266504 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3648. Min Act: -0.1700

Data Index: 5360240 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3955. Min Act: -0.1700

Data Index: 1121863 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.4307. Min Act: -0.1700

Data Index: 8677784 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2974. Min Act: -0.1700

Data Index: 5872581 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3400. Min Act: -0.1700

Data Index: 6812124 (Open Web Text)

Max Activating Token Index: 918

Text #6

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2952. Min Act: -0.1700

Data Index: 5862436 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3119. Min Act: -0.1700

Data Index: 7994677 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2645. Min Act: -0.1700

Data Index: 403643 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2653. Min Act: -0.1700

Data Index: 4288707 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2993. Min Act: -0.1700

Data Index: 8406850 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3018. Min Act: -0.1700

Data Index: 5495854 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3520. Min Act: -0.1700

Data Index: 2174210 (Open Web Text)

Max Activating Token Index: 131

Text #13

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2775. Min Act: -0.1700

Data Index: 2612102 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2627. Min Act: -0.1700

Data Index: 5563837 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2258. Min Act: -0.1700

Data Index: 7321505 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2672. Min Act: -0.1700

Data Index: 1897814 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3098. Min Act: -0.1700

Data Index: 6661949 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.3366. Min Act: -0.1700

Data Index: 1525423 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 4.5064. Min Range: -4.5064

Max Act: 4.2599. Min Act: -0.1700

Data Index: 8154714 (Open Web Text)

Max Activating Token Index: 351