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

Dataset: Open Web Text

Neuron 2891 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: 4.5356. Min Range: -4.5356

Max Act: 4.5356. Min Act: -0.1700

Data Index: 7483643 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.4421. Min Act: -0.1700

Data Index: 4633030 (Open Web Text)

Max Activating Token Index: 564

Text #2

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.2185. Min Act: -0.1700

Data Index: 7541955 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1964. Min Act: -0.1700

Data Index: 8264868 (Open Web Text)

Max Activating Token Index: 496

Text #4

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1444. Min Act: -0.1700

Data Index: 8457500 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1624. Min Act: -0.1700

Data Index: 1762500 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1309. Min Act: -0.1700

Data Index: 6707224 (Open Web Text)

Max Activating Token Index: 281

Text #7

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1091. Min Act: -0.1700

Data Index: 8653556 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1041. Min Act: -0.1700

Data Index: 6376307 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1267. Min Act: -0.1700

Data Index: 2002297 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1188. Min Act: -0.1700

Data Index: 1184551 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0987. Min Act: -0.1700

Data Index: 7761075 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.1097. Min Act: -0.1700

Data Index: 6548979 (Open Web Text)

Max Activating Token Index: 297

Text #13

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0934. Min Act: -0.1700

Data Index: 3158033 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0518. Min Act: -0.1700

Data Index: 7221463 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0540. Min Act: -0.1700

Data Index: 4471249 (Open Web Text)

Max Activating Token Index: 485

Text #16

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0468. Min Act: -0.1700

Data Index: 4396478 (Open Web Text)

Max Activating Token Index: 67

Text #17

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0476. Min Act: -0.1700

Data Index: 4348565 (Open Web Text)

Max Activating Token Index: 246

Text #18

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0473. Min Act: -0.1700

Data Index: 4130340 (Open Web Text)

Max Activating Token Index: 653

Text #19

Max Range: 4.5356. Min Range: -4.5356

Max Act: 4.0588. Min Act: -0.1700

Data Index: 2997536 (Open Web Text)

Max Activating Token Index: 267