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

Dataset: Open Web Text

Neuron 262 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: 3.7552. Min Range: -3.7552

Max Act: 3.7552. Min Act: -0.1700

Data Index: 5165043 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.7338. Min Act: -0.1700

Data Index: 5503967 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.7067. Min Act: -0.1700

Data Index: 4588199 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6968. Min Act: -0.1700

Data Index: 170496 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6733. Min Act: -0.1700

Data Index: 2034212 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6356. Min Act: -0.1700

Data Index: 3294234 (Open Web Text)

Max Activating Token Index: 758

Text #6

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6494. Min Act: -0.1700

Data Index: 4307862 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6584. Min Act: -0.1700

Data Index: 4563970 (Open Web Text)

Max Activating Token Index: 122

Text #8

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6483. Min Act: -0.1700

Data Index: 8480063 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6319. Min Act: -0.1700

Data Index: 5746287 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6263. Min Act: -0.1700

Data Index: 7952335 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6171. Min Act: -0.1700

Data Index: 2793979 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6087. Min Act: -0.1700

Data Index: 2908602 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.6183. Min Act: -0.1700

Data Index: 4860414 (Open Web Text)

Max Activating Token Index: 635

Text #14

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.5841. Min Act: -0.1700

Data Index: 6306051 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.5826. Min Act: -0.1700

Data Index: 6391146 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.5820. Min Act: -0.1700

Data Index: 6897705 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.5655. Min Act: -0.1700

Data Index: 8692852 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.5612. Min Act: -0.1700

Data Index: 3351544 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 3.7552. Min Range: -3.7552

Max Act: 3.5388. Min Act: -0.1700

Data Index: 405367 (Open Web Text)

Max Activating Token Index: 804