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

Dataset: Open Web Text

Neuron 1886 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: 4.0150. Min Range: -4.0150

Max Act: 3.9835. Min Act: -0.1700

Data Index: 7122347 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 4.0150. Min Range: -4.0150

Max Act: 4.0150. Min Act: -0.1700

Data Index: 3303999 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.8004. Min Act: -0.1700

Data Index: 8119668 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.8310. Min Act: -0.1700

Data Index: 2555127 (Open Web Text)

Max Activating Token Index: 699

Text #4

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.8297. Min Act: -0.1700

Data Index: 3546985 (Open Web Text)

Max Activating Token Index: 767

Text #5

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.8477. Min Act: -0.1700

Data Index: 753765 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.8197. Min Act: -0.1700

Data Index: 3001218 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7997. Min Act: -0.1700

Data Index: 804025 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7752. Min Act: -0.1700

Data Index: 3201841 (Open Web Text)

Max Activating Token Index: 426

Text #9

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7797. Min Act: -0.1700

Data Index: 3284067 (Open Web Text)

Max Activating Token Index: 643

Text #10

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7754. Min Act: -0.1700

Data Index: 6010049 (Open Web Text)

Max Activating Token Index: 787

Text #11

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7910. Min Act: -0.1700

Data Index: 3352944 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7527. Min Act: -0.1700

Data Index: 8285168 (Open Web Text)

Max Activating Token Index: 358

Text #13

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7533. Min Act: -0.1700

Data Index: 8185039 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7558. Min Act: -0.1700

Data Index: 6966526 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7564. Min Act: -0.1700

Data Index: 3639778 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7593. Min Act: -0.1700

Data Index: 5039186 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7424. Min Act: -0.1700

Data Index: 5486995 (Open Web Text)

Max Activating Token Index: 604

Text #18

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7123. Min Act: -0.1700

Data Index: 6001238 (Open Web Text)

Max Activating Token Index: 475

Text #19

Max Range: 4.0150. Min Range: -4.0150

Max Act: 3.7585. Min Act: -0.1700

Data Index: 3248176 (Open Web Text)

Max Activating Token Index: 591