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

Dataset: Open Web Text

Neuron 371 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: 3.0826. Min Range: -3.0826

Max Act: 3.0826. Min Act: -0.1700

Data Index: 5204169 (Open Web Text)

Max Activating Token Index: 994

Text #1

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.9379. Min Act: -0.1700

Data Index: 2134989 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.9256. Min Act: -0.1700

Data Index: 5384406 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8992. Min Act: -0.1700

Data Index: 6087057 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8836. Min Act: -0.1700

Data Index: 3767925 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8985. Min Act: -0.1700

Data Index: 7598601 (Open Web Text)

Max Activating Token Index: 933

Text #6

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8900. Min Act: -0.1700

Data Index: 6323352 (Open Web Text)

Max Activating Token Index: 628

Text #7

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8824. Min Act: -0.1700

Data Index: 5876398 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8686. Min Act: -0.1700

Data Index: 655385 (Open Web Text)

Max Activating Token Index: 377

Text #9

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8763. Min Act: -0.1700

Data Index: 81218 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8668. Min Act: -0.1700

Data Index: 2159197 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8653. Min Act: -0.1700

Data Index: 4565777 (Open Web Text)

Max Activating Token Index: 548

Text #12

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8635. Min Act: -0.1700

Data Index: 2367239 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8410. Min Act: -0.1700

Data Index: 7113008 (Open Web Text)

Max Activating Token Index: 853

Text #14

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8394. Min Act: -0.1700

Data Index: 7014104 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8630. Min Act: -0.1700

Data Index: 6752246 (Open Web Text)

Max Activating Token Index: 238

Text #16

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8148. Min Act: -0.1700

Data Index: 5189894 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8335. Min Act: -0.1700

Data Index: 1939630 (Open Web Text)

Max Activating Token Index: 276

Text #18

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8143. Min Act: -0.1700

Data Index: 1426013 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 3.0826. Min Range: -3.0826

Max Act: 2.8292. Min Act: -0.1700

Data Index: 4193987 (Open Web Text)

Max Activating Token Index: 371