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

Dataset: Open Web Text

Neuron 889 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: 2.7644. Min Range: -2.7644

Max Act: 2.7565. Min Act: -0.1700

Data Index: 7077038 (Open Web Text)

Max Activating Token Index: 297

Text #1

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.7554. Min Act: -0.1700

Data Index: 6100419 (Open Web Text)

Max Activating Token Index: 809

Text #2

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.7644. Min Act: -0.1700

Data Index: 5847145 (Open Web Text)

Max Activating Token Index: 840

Text #3

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.7371. Min Act: -0.1700

Data Index: 1961615 (Open Web Text)

Max Activating Token Index: 331

Text #4

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6840. Min Act: -0.1700

Data Index: 8278277 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6566. Min Act: -0.1700

Data Index: 4516025 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6493. Min Act: -0.1700

Data Index: 6603207 (Open Web Text)

Max Activating Token Index: 496

Text #7

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6343. Min Act: -0.1700

Data Index: 911691 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6337. Min Act: -0.1700

Data Index: 2992193 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6161. Min Act: -0.1700

Data Index: 6918199 (Open Web Text)

Max Activating Token Index: 245

Text #10

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6249. Min Act: -0.1700

Data Index: 2499464 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6153. Min Act: -0.1700

Data Index: 1381123 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5968. Min Act: -0.1700

Data Index: 5571384 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.6098. Min Act: -0.1700

Data Index: 170068 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5934. Min Act: -0.1700

Data Index: 749813 (Open Web Text)

Max Activating Token Index: 807

Text #15

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5845. Min Act: -0.1700

Data Index: 7093697 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5777. Min Act: -0.1700

Data Index: 8530581 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5612. Min Act: -0.1700

Data Index: 2368102 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5823. Min Act: -0.1700

Data Index: 4885410 (Open Web Text)

Max Activating Token Index: 376

Text #19

Max Range: 2.7644. Min Range: -2.7644

Max Act: 2.5731. Min Act: -0.1700

Data Index: 5264586 (Open Web Text)

Max Activating Token Index: 7