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

Dataset: Open Web Text

Neuron 1763 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: 3.7560. Min Range: -3.7560

Max Act: 3.7326. Min Act: -0.1700

Data Index: 6314889 (Open Web Text)

Max Activating Token Index: 173

Text #1

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.7560. Min Act: -0.1700

Data Index: 445409 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.7429. Min Act: -0.1700

Data Index: 6617942 (Open Web Text)

Max Activating Token Index: 870

Text #3

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6524. Min Act: -0.1700

Data Index: 8458653 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6308. Min Act: -0.1700

Data Index: 2513114 (Open Web Text)

Max Activating Token Index: 737

Text #5

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6102. Min Act: -0.1700

Data Index: 2984484 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6120. Min Act: -0.1700

Data Index: 1646701 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.6084. Min Act: -0.1700

Data Index: 8779314 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5965. Min Act: -0.1700

Data Index: 6159090 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5531. Min Act: -0.1700

Data Index: 6669726 (Open Web Text)

Max Activating Token Index: 783

Text #10

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5733. Min Act: -0.1700

Data Index: 2121683 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5632. Min Act: -0.1700

Data Index: 6980662 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5301. Min Act: -0.1700

Data Index: 6579327 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5396. Min Act: -0.1700

Data Index: 628664 (Open Web Text)

Max Activating Token Index: 291

Text #14

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5142. Min Act: -0.1700

Data Index: 3844394 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5164. Min Act: -0.1700

Data Index: 5595598 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5248. Min Act: -0.1700

Data Index: 5800440 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5061. Min Act: -0.1700

Data Index: 5097664 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.4978. Min Act: -0.1700

Data Index: 1673143 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 3.7560. Min Range: -3.7560

Max Act: 3.5111. Min Act: -0.1700

Data Index: 4066698 (Open Web Text)

Max Activating Token Index: 687