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

Dataset: Open Web Text

Neuron 2333 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: 4.8326. Min Range: -4.8326

Max Act: 4.8326. Min Act: -0.1700

Data Index: 7467429 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.7568. Min Act: -0.1700

Data Index: 7453574 (Open Web Text)

Max Activating Token Index: 853

Text #2

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.6778. Min Act: -0.1700

Data Index: 3076705 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.6706. Min Act: -0.1700

Data Index: 8759071 (Open Web Text)

Max Activating Token Index: 839

Text #4

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.6283. Min Act: -0.1700

Data Index: 2284211 (Open Web Text)

Max Activating Token Index: 94

Text #5

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.6075. Min Act: -0.1700

Data Index: 3927181 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5890. Min Act: -0.1700

Data Index: 292763 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5427. Min Act: -0.1700

Data Index: 501798 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5641. Min Act: -0.1700

Data Index: 1156883 (Open Web Text)

Max Activating Token Index: 148

Text #9

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5456. Min Act: -0.1700

Data Index: 6365026 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5532. Min Act: -0.1700

Data Index: 3766121 (Open Web Text)

Max Activating Token Index: 419

Text #11

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5615. Min Act: -0.1700

Data Index: 5733822 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5163. Min Act: -0.1700

Data Index: 7003298 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5446. Min Act: -0.1700

Data Index: 6642851 (Open Web Text)

Max Activating Token Index: 245

Text #14

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5224. Min Act: -0.1700

Data Index: 1156881 (Open Web Text)

Max Activating Token Index: 155

Text #15

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5328. Min Act: -0.1700

Data Index: 871235 (Open Web Text)

Max Activating Token Index: 320

Text #16

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5506. Min Act: -0.1700

Data Index: 4179950 (Open Web Text)

Max Activating Token Index: 379

Text #17

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5313. Min Act: -0.1700

Data Index: 4891095 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.5123. Min Act: -0.1700

Data Index: 8803757 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 4.8326. Min Range: -4.8326

Max Act: 4.4941. Min Act: -0.1700

Data Index: 70042 (Open Web Text)

Max Activating Token Index: 612