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

Dataset: Open Web Text

Neuron 2930 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: 4.5989. Min Range: -4.5989

Max Act: 4.5989. Min Act: -0.1700

Data Index: 476031 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.5062. Min Act: -0.1700

Data Index: 3473543 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.5063. Min Act: -0.1700

Data Index: 8627036 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.4523. Min Act: -0.1700

Data Index: 4356116 (Open Web Text)

Max Activating Token Index: 500

Text #4

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.3689. Min Act: -0.1700

Data Index: 5948883 (Open Web Text)

Max Activating Token Index: 421

Text #5

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.3468. Min Act: -0.1700

Data Index: 2813251 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.3311. Min Act: -0.1700

Data Index: 3678119 (Open Web Text)

Max Activating Token Index: 186

Text #7

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.3395. Min Act: -0.1700

Data Index: 3627741 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2509. Min Act: -0.1700

Data Index: 255400 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2752. Min Act: -0.1700

Data Index: 7811847 (Open Web Text)

Max Activating Token Index: 572

Text #10

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2438. Min Act: -0.1700

Data Index: 6308835 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2094. Min Act: -0.1700

Data Index: 5989453 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2235. Min Act: -0.1700

Data Index: 4179743 (Open Web Text)

Max Activating Token Index: 233

Text #13

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.1772. Min Act: -0.1700

Data Index: 6869384 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.1711. Min Act: -0.1700

Data Index: 6494573 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.1946. Min Act: -0.1700

Data Index: 3168205 (Open Web Text)

Max Activating Token Index: 614

Text #16

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2198. Min Act: -0.1700

Data Index: 8048761 (Open Web Text)

Max Activating Token Index: 908

Text #17

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.1925. Min Act: -0.1700

Data Index: 6798821 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.2413. Min Act: -0.1700

Data Index: 6715121 (Open Web Text)

Max Activating Token Index: 162

Text #19

Max Range: 4.5989. Min Range: -4.5989

Max Act: 4.1967. Min Act: -0.1700

Data Index: 7725873 (Open Web Text)

Max Activating Token Index: 278