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

Dataset: Open Web Text

Neuron 1193 in Layer 4

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: 5.5121. Min Range: -5.5121

Max Act: 5.5121. Min Act: -0.1700

Data Index: 8571827 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.4381. Min Act: -0.1700

Data Index: 7704174 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.4468. Min Act: -0.1700

Data Index: 6811004 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.3886. Min Act: -0.1700

Data Index: 4567215 (Open Web Text)

Max Activating Token Index: 978

Text #4

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.4268. Min Act: -0.1700

Data Index: 4631838 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.4466. Min Act: -0.1700

Data Index: 5704081 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.3155. Min Act: -0.1700

Data Index: 5639291 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.3568. Min Act: -0.1700

Data Index: 4547614 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.3292. Min Act: -0.1700

Data Index: 6119970 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2674. Min Act: -0.1700

Data Index: 8814536 (Open Web Text)

Max Activating Token Index: 149

Text #10

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2687. Min Act: -0.1700

Data Index: 1276006 (Open Web Text)

Max Activating Token Index: 610

Text #11

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2789. Min Act: -0.1700

Data Index: 7399793 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2497. Min Act: -0.1700

Data Index: 7286926 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2388. Min Act: -0.1700

Data Index: 1575738 (Open Web Text)

Max Activating Token Index: 969

Text #14

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2569. Min Act: -0.1700

Data Index: 6106270 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2237. Min Act: -0.1700

Data Index: 7174597 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2311. Min Act: -0.1700

Data Index: 4907315 (Open Web Text)

Max Activating Token Index: 762

Text #17

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2366. Min Act: -0.1700

Data Index: 2695308 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.2089. Min Act: -0.1700

Data Index: 3034235 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 5.5121. Min Range: -5.5121

Max Act: 5.1976. Min Act: -0.1700

Data Index: 666049 (Open Web Text)

Max Activating Token Index: 390