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

Dataset: Open Web Text

Neuron 1725 in Layer 6

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: 2.9041. Min Range: -2.9041

Max Act: 2.9041. Min Act: -0.1700

Data Index: 6181999 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.8046. Min Act: -0.1700

Data Index: 2262896 (Open Web Text)

Max Activating Token Index: 630

Text #2

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7919. Min Act: -0.1700

Data Index: 6945050 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7762. Min Act: -0.1700

Data Index: 4856935 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7849. Min Act: -0.1700

Data Index: 4459046 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7602. Min Act: -0.1700

Data Index: 3113796 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7667. Min Act: -0.1700

Data Index: 1302214 (Open Web Text)

Max Activating Token Index: 55

Text #7

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7724. Min Act: -0.1700

Data Index: 5794778 (Open Web Text)

Max Activating Token Index: 758

Text #8

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7408. Min Act: -0.1700

Data Index: 4651146 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7318. Min Act: -0.1700

Data Index: 6088508 (Open Web Text)

Max Activating Token Index: 357

Text #10

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7463. Min Act: -0.1700

Data Index: 4716112 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7393. Min Act: -0.1700

Data Index: 4139851 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7549. Min Act: -0.1700

Data Index: 810035 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7206. Min Act: -0.1700

Data Index: 2515376 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7417. Min Act: -0.1700

Data Index: 6632754 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7337. Min Act: -0.1700

Data Index: 3263924 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7286. Min Act: -0.1700

Data Index: 5154615 (Open Web Text)

Max Activating Token Index: 579

Text #17

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7093. Min Act: -0.1700

Data Index: 3027225 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7111. Min Act: -0.1700

Data Index: 4693464 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 2.9041. Min Range: -2.9041

Max Act: 2.7256. Min Act: -0.1700

Data Index: 6616170 (Open Web Text)

Max Activating Token Index: 270