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

Dataset: Open Web Text

Neuron 2976 in Layer 6

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: 6.2088. Min Range: -6.2088

Max Act: 6.2088. Min Act: -0.1700

Data Index: 5389658 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.6897. Min Act: -0.1700

Data Index: 3636954 (Open Web Text)

Max Activating Token Index: 328

Text #2

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.5466. Min Act: -0.1700

Data Index: 1060218 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.5368. Min Act: -0.1700

Data Index: 4303200 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4990. Min Act: -0.1700

Data Index: 4001069 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4761. Min Act: -0.1700

Data Index: 5628971 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4789. Min Act: -0.1700

Data Index: 7601118 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4651. Min Act: -0.1700

Data Index: 7078511 (Open Web Text)

Max Activating Token Index: 876

Text #8

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4595. Min Act: -0.1700

Data Index: 6833341 (Open Web Text)

Max Activating Token Index: 109

Text #9

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4598. Min Act: -0.1700

Data Index: 8282891 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4716. Min Act: -0.1700

Data Index: 2478773 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4115. Min Act: -0.1700

Data Index: 7114480 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.4080. Min Act: -0.1700

Data Index: 8250305 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.3918. Min Act: -0.1700

Data Index: 6827671 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.3880. Min Act: -0.1700

Data Index: 3718426 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.3662. Min Act: -0.1700

Data Index: 7601119 (Open Web Text)

Max Activating Token Index: 756

Text #16

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.2818. Min Act: -0.1700

Data Index: 6138469 (Open Web Text)

Max Activating Token Index: 701

Text #17

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.3337. Min Act: -0.1700

Data Index: 5494342 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.2782. Min Act: -0.1700

Data Index: 6808036 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 6.2088. Min Range: -6.2088

Max Act: 5.2944. Min Act: -0.1700

Data Index: 2775481 (Open Web Text)

Max Activating Token Index: 664