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

Dataset: Open Web Text

Neuron 592 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: 4.8180. Min Range: -4.8180

Max Act: 4.8180. Min Act: -0.1700

Data Index: 4919842 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.7199. Min Act: -0.1700

Data Index: 7798084 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6252. Min Act: -0.1700

Data Index: 3689379 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5236. Min Act: -0.1700

Data Index: 1175431 (Open Web Text)

Max Activating Token Index: 624

Text #4

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5453. Min Act: -0.1700

Data Index: 1175432 (Open Web Text)

Max Activating Token Index: 660

Text #5

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5186. Min Act: -0.1700

Data Index: 6267771 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5060. Min Act: -0.1700

Data Index: 6267770 (Open Web Text)

Max Activating Token Index: 319

Text #7

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5184. Min Act: -0.1700

Data Index: 1142891 (Open Web Text)

Max Activating Token Index: 642

Text #8

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5099. Min Act: -0.1700

Data Index: 2090563 (Open Web Text)

Max Activating Token Index: 845

Text #9

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4874. Min Act: -0.1700

Data Index: 7339441 (Open Web Text)

Max Activating Token Index: 328

Text #10

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4630. Min Act: -0.1700

Data Index: 7216329 (Open Web Text)

Max Activating Token Index: 932

Text #11

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4598. Min Act: -0.1700

Data Index: 7510208 (Open Web Text)

Max Activating Token Index: 684

Text #12

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4480. Min Act: -0.1700

Data Index: 5677271 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4066. Min Act: -0.1700

Data Index: 6267769 (Open Web Text)

Max Activating Token Index: 501

Text #14

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4447. Min Act: -0.1700

Data Index: 7798087 (Open Web Text)

Max Activating Token Index: 253

Text #15

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4205. Min Act: -0.1700

Data Index: 1175430 (Open Web Text)

Max Activating Token Index: 806

Text #16

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.4171. Min Act: -0.1700

Data Index: 3482477 (Open Web Text)

Max Activating Token Index: 552

Text #17

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.3798. Min Act: -0.1700

Data Index: 1338308 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.3926. Min Act: -0.1700

Data Index: 4988135 (Open Web Text)

Max Activating Token Index: 569

Text #19

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.3869. Min Act: -0.1700

Data Index: 7798085 (Open Web Text)

Max Activating Token Index: 459