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

Dataset: Open Web Text

Neuron 2316 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: 3.6912. Min Range: -3.6912

Max Act: 3.6905. Min Act: -0.1700

Data Index: 879382 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6912. Min Act: -0.1700

Data Index: 1949482 (Open Web Text)

Max Activating Token Index: 342

Text #2

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6762. Min Act: -0.1700

Data Index: 269651 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6281. Min Act: -0.1700

Data Index: 5896716 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6139. Min Act: -0.1700

Data Index: 6107190 (Open Web Text)

Max Activating Token Index: 792

Text #5

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6130. Min Act: -0.1700

Data Index: 5271736 (Open Web Text)

Max Activating Token Index: 354

Text #6

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6092. Min Act: -0.1700

Data Index: 6540969 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5978. Min Act: -0.1700

Data Index: 4584788 (Open Web Text)

Max Activating Token Index: 759

Text #8

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5845. Min Act: -0.1700

Data Index: 5851203 (Open Web Text)

Max Activating Token Index: 197

Text #9

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5658. Min Act: -0.1700

Data Index: 2288967 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5740. Min Act: -0.1700

Data Index: 3927585 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5431. Min Act: -0.1700

Data Index: 7138660 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5469. Min Act: -0.1700

Data Index: 4878627 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5457. Min Act: -0.1700

Data Index: 3683100 (Open Web Text)

Max Activating Token Index: 636

Text #14

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5337. Min Act: -0.1700

Data Index: 8211805 (Open Web Text)

Max Activating Token Index: 709

Text #15

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5232. Min Act: -0.1700

Data Index: 188358 (Open Web Text)

Max Activating Token Index: 511

Text #16

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5470. Min Act: -0.1700

Data Index: 238676 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5184. Min Act: -0.1700

Data Index: 6873137 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5289. Min Act: -0.1700

Data Index: 6764991 (Open Web Text)

Max Activating Token Index: 336

Text #19

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5108. Min Act: -0.1700

Data Index: 6877289 (Open Web Text)

Max Activating Token Index: 895