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

Dataset: Open Web Text

Neuron 287 in Layer 1

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: 1.9271. Min Range: -1.9271

Max Act: 1.9271. Min Act: -0.1700

Data Index: 934870 (Open Web Text)

Max Activating Token Index: 220

Text #1

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8928. Min Act: -0.1700

Data Index: 5508228 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8884. Min Act: -0.1700

Data Index: 5508221 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8580. Min Act: -0.1700

Data Index: 8003014 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8238. Min Act: -0.1700

Data Index: 8003021 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8211. Min Act: -0.1700

Data Index: 5177470 (Open Web Text)

Max Activating Token Index: 526

Text #6

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8207. Min Act: -0.1700

Data Index: 5931501 (Open Web Text)

Max Activating Token Index: 276

Text #7

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8105. Min Act: -0.1700

Data Index: 6836580 (Open Web Text)

Max Activating Token Index: 935

Text #8

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.8128. Min Act: -0.1700

Data Index: 7584016 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7951. Min Act: -0.1700

Data Index: 6746384 (Open Web Text)

Max Activating Token Index: 748

Text #10

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7971. Min Act: -0.1700

Data Index: 977046 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7976. Min Act: -0.1700

Data Index: 255996 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7990. Min Act: -0.1700

Data Index: 3710164 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7812. Min Act: -0.1700

Data Index: 1261252 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7975. Min Act: -0.1700

Data Index: 4440396 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7894. Min Act: -0.1700

Data Index: 6411982 (Open Web Text)

Max Activating Token Index: 684

Text #16

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7782. Min Act: -0.1700

Data Index: 7998574 (Open Web Text)

Max Activating Token Index: 153

Text #17

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7714. Min Act: -0.1700

Data Index: 6266558 (Open Web Text)

Max Activating Token Index: 378

Text #18

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7661. Min Act: -0.1700

Data Index: 6266557 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 1.9271. Min Range: -1.9271

Max Act: 1.7707. Min Act: -0.1700

Data Index: 1261249 (Open Web Text)

Max Activating Token Index: 265