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

Dataset: Open Web Text

Neuron 1139 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: 4.3720. Min Range: -4.3720

Max Act: 4.3720. Min Act: -0.1700

Data Index: 7928979 (Open Web Text)

Max Activating Token Index: 159

Text #1

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2939. Min Act: -0.1700

Data Index: 2057116 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.3188. Min Act: -0.1700

Data Index: 6122805 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.3009. Min Act: -0.1700

Data Index: 2503395 (Open Web Text)

Max Activating Token Index: 179

Text #4

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2827. Min Act: -0.1700

Data Index: 5303481 (Open Web Text)

Max Activating Token Index: 146

Text #5

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2804. Min Act: -0.1700

Data Index: 5790993 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2840. Min Act: -0.1700

Data Index: 6183685 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2673. Min Act: -0.1700

Data Index: 4099067 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2696. Min Act: -0.1700

Data Index: 6197821 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2801. Min Act: -0.1700

Data Index: 1332344 (Open Web Text)

Max Activating Token Index: 200

Text #10

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2888. Min Act: -0.1700

Data Index: 3578453 (Open Web Text)

Max Activating Token Index: 56

Text #11

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2812. Min Act: -0.1700

Data Index: 8474601 (Open Web Text)

Max Activating Token Index: 236

Text #12

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2440. Min Act: -0.1700

Data Index: 4243687 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2651. Min Act: -0.1700

Data Index: 4357170 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2485. Min Act: -0.1700

Data Index: 8616069 (Open Web Text)

Max Activating Token Index: 216

Text #15

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2274. Min Act: -0.1700

Data Index: 1307326 (Open Web Text)

Max Activating Token Index: 100

Text #16

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2415. Min Act: -0.1700

Data Index: 6357959 (Open Web Text)

Max Activating Token Index: 143

Text #17

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2326. Min Act: -0.1700

Data Index: 6326207 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2403. Min Act: -0.1700

Data Index: 2073169 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 4.3720. Min Range: -4.3720

Max Act: 4.2394. Min Act: -0.1700

Data Index: 988532 (Open Web Text)

Max Activating Token Index: 536