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

Dataset: Open Web Text

Neuron 1481 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: 4.6262. Min Range: -4.6262

Max Act: 4.6262. Min Act: -0.1700

Data Index: 4413057 (Open Web Text)

Max Activating Token Index: 200

Text #1

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.6139. Min Act: -0.1700

Data Index: 3897718 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5992. Min Act: -0.1700

Data Index: 1523592 (Open Web Text)

Max Activating Token Index: 371

Text #3

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5943. Min Act: -0.1700

Data Index: 5099275 (Open Web Text)

Max Activating Token Index: 402

Text #4

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5817. Min Act: -0.1700

Data Index: 2717738 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5840. Min Act: -0.1700

Data Index: 2151273 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5437. Min Act: -0.1700

Data Index: 2463616 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5615. Min Act: -0.1700

Data Index: 6674426 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5278. Min Act: -0.1700

Data Index: 5960940 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5269. Min Act: -0.1700

Data Index: 220615 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5504. Min Act: -0.1700

Data Index: 5467430 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.4909. Min Act: -0.1700

Data Index: 93584 (Open Web Text)

Max Activating Token Index: 353

Text #12

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.4886. Min Act: -0.1700

Data Index: 6041342 (Open Web Text)

Max Activating Token Index: 257

Text #13

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5023. Min Act: -0.1700

Data Index: 2376529 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.4872. Min Act: -0.1700

Data Index: 3824953 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5108. Min Act: -0.1700

Data Index: 6307014 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.4984. Min Act: -0.1700

Data Index: 748185 (Open Web Text)

Max Activating Token Index: 215

Text #17

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5076. Min Act: -0.1700

Data Index: 7878829 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.4953. Min Act: -0.1700

Data Index: 4631418 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 4.6262. Min Range: -4.6262

Max Act: 4.5131. Min Act: -0.1700

Data Index: 120720 (Open Web Text)

Max Activating Token Index: 132