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

Dataset: Open Web Text

Neuron 184 in Layer 5

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: 6.0220. Min Range: -6.0220

Max Act: 6.0220. Min Act: -0.1700

Data Index: 5171739 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.9515. Min Act: -0.1700

Data Index: 1450834 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.7354. Min Act: -0.1700

Data Index: 1693010 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6854. Min Act: -0.1700

Data Index: 3810955 (Open Web Text)

Max Activating Token Index: 316

Text #4

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6596. Min Act: -0.1700

Data Index: 4576289 (Open Web Text)

Max Activating Token Index: 847

Text #5

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6646. Min Act: -0.1700

Data Index: 7876080 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5977. Min Act: -0.1700

Data Index: 8589149 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6248. Min Act: -0.1700

Data Index: 576343 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6286. Min Act: -0.1700

Data Index: 6644809 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6443. Min Act: -0.1700

Data Index: 6236060 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6168. Min Act: -0.1700

Data Index: 8470925 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6132. Min Act: -0.1700

Data Index: 8798358 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.6001. Min Act: -0.1700

Data Index: 661839 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5643. Min Act: -0.1700

Data Index: 2560631 (Open Web Text)

Max Activating Token Index: 820

Text #14

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5652. Min Act: -0.1700

Data Index: 5499937 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5019. Min Act: -0.1700

Data Index: 4156788 (Open Web Text)

Max Activating Token Index: 908

Text #16

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5179. Min Act: -0.1700

Data Index: 1041486 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5220. Min Act: -0.1700

Data Index: 4389999 (Open Web Text)

Max Activating Token Index: 263

Text #18

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5089. Min Act: -0.1700

Data Index: 8490854 (Open Web Text)

Max Activating Token Index: 717

Text #19

Max Range: 6.0220. Min Range: -6.0220

Max Act: 5.5288. Min Act: -0.1700

Data Index: 5339972 (Open Web Text)

Max Activating Token Index: 117