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

Dataset: Open Web Text

Neuron 2578 in Layer 1

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: 3.9560. Min Range: -3.9560

Max Act: 3.9363. Min Act: -0.1700

Data Index: 1072073 (Open Web Text)

Max Activating Token Index: 492

Text #1

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9337. Min Act: -0.1700

Data Index: 3220164 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9323. Min Act: -0.1700

Data Index: 3268409 (Open Web Text)

Max Activating Token Index: 387

Text #3

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9560. Min Act: -0.1700

Data Index: 1774029 (Open Web Text)

Max Activating Token Index: 132

Text #4

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9481. Min Act: -0.1700

Data Index: 4092725 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9278. Min Act: -0.1700

Data Index: 2329125 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9466. Min Act: -0.1700

Data Index: 6435850 (Open Web Text)

Max Activating Token Index: 640

Text #7

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9174. Min Act: -0.1700

Data Index: 3032089 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.8883. Min Act: -0.1700

Data Index: 1840352 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9040. Min Act: -0.1700

Data Index: 7641323 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9255. Min Act: -0.1700

Data Index: 7250526 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9136. Min Act: -0.1700

Data Index: 6302719 (Open Web Text)

Max Activating Token Index: 681

Text #12

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9194. Min Act: -0.1700

Data Index: 5428952 (Open Web Text)

Max Activating Token Index: 263

Text #13

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9178. Min Act: -0.1700

Data Index: 4781565 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.9038. Min Act: -0.1700

Data Index: 2742608 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.8781. Min Act: -0.1700

Data Index: 2192036 (Open Web Text)

Max Activating Token Index: 456

Text #16

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.8649. Min Act: -0.1700

Data Index: 890874 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.8723. Min Act: -0.1700

Data Index: 2556739 (Open Web Text)

Max Activating Token Index: 852

Text #18

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.8951. Min Act: -0.1700

Data Index: 2740658 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 3.9560. Min Range: -3.9560

Max Act: 3.8837. Min Act: -0.1700

Data Index: 658507 (Open Web Text)

Max Activating Token Index: 710