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

Dataset: Open Web Text

Neuron 1591 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: 3.8883. Min Range: -3.8883

Max Act: 3.8883. Min Act: -0.1700

Data Index: 4978316 (Open Web Text)

Max Activating Token Index: 955

Text #1

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8260. Min Act: -0.1700

Data Index: 2366343 (Open Web Text)

Max Activating Token Index: 549

Text #2

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8593. Min Act: -0.1700

Data Index: 1102198 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8644. Min Act: -0.1700

Data Index: 4248978 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8833. Min Act: -0.1700

Data Index: 7205207 (Open Web Text)

Max Activating Token Index: 625

Text #5

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8736. Min Act: -0.1700

Data Index: 8543694 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8616. Min Act: -0.1700

Data Index: 4378027 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8520. Min Act: -0.1700

Data Index: 7807014 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8483. Min Act: -0.1700

Data Index: 3568429 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8368. Min Act: -0.1700

Data Index: 5789475 (Open Web Text)

Max Activating Token Index: 156

Text #10

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8654. Min Act: -0.1700

Data Index: 5350054 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8298. Min Act: -0.1700

Data Index: 3618089 (Open Web Text)

Max Activating Token Index: 906

Text #12

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8447. Min Act: -0.1700

Data Index: 3093350 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8144. Min Act: -0.1700

Data Index: 3000367 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8119. Min Act: -0.1700

Data Index: 435525 (Open Web Text)

Max Activating Token Index: 778

Text #15

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8483. Min Act: -0.1700

Data Index: 629920 (Open Web Text)

Max Activating Token Index: 935

Text #16

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8221. Min Act: -0.1700

Data Index: 4226451 (Open Web Text)

Max Activating Token Index: 964

Text #17

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8126. Min Act: -0.1700

Data Index: 5694730 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.8036. Min Act: -0.1700

Data Index: 1392347 (Open Web Text)

Max Activating Token Index: 1018

Text #19

Max Range: 3.8883. Min Range: -3.8883

Max Act: 3.7547. Min Act: -0.1700

Data Index: 1045803 (Open Web Text)

Max Activating Token Index: 196