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

Dataset: Open Web Text

Neuron 1416 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: 4.6590. Min Range: -4.6590

Max Act: 4.6590. Min Act: -0.1700

Data Index: 3125774 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.4938. Min Act: -0.1700

Data Index: 2872432 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.3053. Min Act: -0.1700

Data Index: 4322043 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.3198. Min Act: -0.1700

Data Index: 483450 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.3050. Min Act: -0.1700

Data Index: 2683206 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.3114. Min Act: -0.1700

Data Index: 3035170 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2838. Min Act: -0.1700

Data Index: 2512124 (Open Web Text)

Max Activating Token Index: 118

Text #7

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2538. Min Act: -0.1700

Data Index: 2083718 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2449. Min Act: -0.1700

Data Index: 4978386 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2538. Min Act: -0.1700

Data Index: 3112597 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2564. Min Act: -0.1700

Data Index: 8415338 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2272. Min Act: -0.1700

Data Index: 755156 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2538. Min Act: -0.1700

Data Index: 8107470 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2538. Min Act: -0.1700

Data Index: 2905434 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2059. Min Act: -0.1700

Data Index: 8272472 (Open Web Text)

Max Activating Token Index: 849

Text #15

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2151. Min Act: -0.1700

Data Index: 8166144 (Open Web Text)

Max Activating Token Index: 320

Text #16

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2420. Min Act: -0.1700

Data Index: 2601232 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2458. Min Act: -0.1700

Data Index: 6449398 (Open Web Text)

Max Activating Token Index: 468

Text #18

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2211. Min Act: -0.1700

Data Index: 2745765 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.1874. Min Act: -0.1700

Data Index: 494080 (Open Web Text)

Max Activating Token Index: 297