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

Dataset: Open Web Text

Neuron 1683 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: 2.0148. Min Range: -2.0148

Max Act: 2.0148. Min Act: -0.1700

Data Index: 5127073 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9671. Min Act: -0.1700

Data Index: 4795873 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9853. Min Act: -0.1700

Data Index: 2479342 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9558. Min Act: -0.1700

Data Index: 2646330 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9569. Min Act: -0.1700

Data Index: 4103813 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9494. Min Act: -0.1700

Data Index: 446860 (Open Web Text)

Max Activating Token Index: 517

Text #6

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9264. Min Act: -0.1700

Data Index: 7417087 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9363. Min Act: -0.1700

Data Index: 8358407 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9294. Min Act: -0.1700

Data Index: 5507067 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9440. Min Act: -0.1700

Data Index: 5892062 (Open Web Text)

Max Activating Token Index: 415

Text #10

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9150. Min Act: -0.1700

Data Index: 7214606 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9094. Min Act: -0.1700

Data Index: 6024388 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9106. Min Act: -0.1700

Data Index: 1911549 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9220. Min Act: -0.1700

Data Index: 8078445 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9299. Min Act: -0.1700

Data Index: 5681593 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9068. Min Act: -0.1700

Data Index: 7720940 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9139. Min Act: -0.1700

Data Index: 7423616 (Open Web Text)

Max Activating Token Index: 93

Text #17

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9179. Min Act: -0.1700

Data Index: 6497240 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9101. Min Act: -0.1699

Data Index: 6476511 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 2.0148. Min Range: -2.0148

Max Act: 1.9040. Min Act: -0.1700

Data Index: 1713555 (Open Web Text)

Max Activating Token Index: 240