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

Dataset: Open Web Text

Neuron 1774 in Layer 2

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: 3.8972. Min Range: -3.8972

Max Act: 3.8972. Min Act: -0.1700

Data Index: 1435467 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7987. Min Act: -0.1700

Data Index: 4949565 (Open Web Text)

Max Activating Token Index: 375

Text #2

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7772. Min Act: -0.1700

Data Index: 8289063 (Open Web Text)

Max Activating Token Index: 746

Text #3

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7307. Min Act: -0.1700

Data Index: 4676513 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7270. Min Act: -0.1700

Data Index: 7196515 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7137. Min Act: -0.1700

Data Index: 7515966 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6584. Min Act: -0.1700

Data Index: 4671026 (Open Web Text)

Max Activating Token Index: 140

Text #7

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6748. Min Act: -0.1700

Data Index: 6074077 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6984. Min Act: -0.1700

Data Index: 689904 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6881. Min Act: -0.1700

Data Index: 5415092 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6916. Min Act: -0.1700

Data Index: 3293942 (Open Web Text)

Max Activating Token Index: 471

Text #11

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6799. Min Act: -0.1700

Data Index: 7183866 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6805. Min Act: -0.1700

Data Index: 3935449 (Open Web Text)

Max Activating Token Index: 529

Text #13

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6992. Min Act: -0.1700

Data Index: 5565900 (Open Web Text)

Max Activating Token Index: 658

Text #14

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6714. Min Act: -0.1700

Data Index: 689902 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6483. Min Act: -0.1700

Data Index: 1199488 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6691. Min Act: -0.1700

Data Index: 6755023 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6665. Min Act: -0.1700

Data Index: 6560573 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6726. Min Act: -0.1700

Data Index: 4852329 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6394. Min Act: -0.1700

Data Index: 4271028 (Open Web Text)

Max Activating Token Index: 702