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

Dataset: Open Web Text

Neuron 925 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: 3.7231. Min Range: -3.7231

Max Act: 3.7231. Min Act: -0.1700

Data Index: 754927 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.6510. Min Act: -0.1700

Data Index: 6620723 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5942. Min Act: -0.1700

Data Index: 7226690 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5936. Min Act: -0.1700

Data Index: 5448034 (Open Web Text)

Max Activating Token Index: 188

Text #4

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5971. Min Act: -0.1700

Data Index: 5074490 (Open Web Text)

Max Activating Token Index: 342

Text #5

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5951. Min Act: -0.1700

Data Index: 6396874 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5938. Min Act: -0.1700

Data Index: 1950083 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5705. Min Act: -0.1700

Data Index: 1085738 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5827. Min Act: -0.1700

Data Index: 6164391 (Open Web Text)

Max Activating Token Index: 738

Text #9

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5593. Min Act: -0.1700

Data Index: 7704606 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5510. Min Act: -0.1700

Data Index: 3753380 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5527. Min Act: -0.1700

Data Index: 5105172 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5506. Min Act: -0.1700

Data Index: 3802443 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5265. Min Act: -0.1700

Data Index: 3493256 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5013. Min Act: -0.1700

Data Index: 118997 (Open Web Text)

Max Activating Token Index: 1008

Text #15

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.5168. Min Act: -0.1700

Data Index: 2315088 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.4931. Min Act: -0.1700

Data Index: 1718848 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.4976. Min Act: -0.1700

Data Index: 7853144 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.4930. Min Act: -0.1700

Data Index: 4759475 (Open Web Text)

Max Activating Token Index: 245

Text #19

Max Range: 3.7231. Min Range: -3.7231

Max Act: 3.4763. Min Act: -0.1700

Data Index: 5760418 (Open Web Text)

Max Activating Token Index: 192