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

Dataset: Open Web Text

Neuron 1250 in Layer 5

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: 3.5908. Min Range: -3.5908

Max Act: 3.5908. Min Act: -0.1700

Data Index: 5829389 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5591. Min Act: -0.1700

Data Index: 5483976 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5662. Min Act: -0.1700

Data Index: 3205670 (Open Web Text)

Max Activating Token Index: 586

Text #3

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5253. Min Act: -0.1700

Data Index: 5829388 (Open Web Text)

Max Activating Token Index: 841

Text #4

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5261. Min Act: -0.1700

Data Index: 2410716 (Open Web Text)

Max Activating Token Index: 252

Text #5

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4901. Min Act: -0.1700

Data Index: 980117 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4974. Min Act: -0.1700

Data Index: 6533453 (Open Web Text)

Max Activating Token Index: 999

Text #7

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5211. Min Act: -0.1700

Data Index: 4096402 (Open Web Text)

Max Activating Token Index: 300

Text #8

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5016. Min Act: -0.1700

Data Index: 4319359 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5071. Min Act: -0.1700

Data Index: 2064333 (Open Web Text)

Max Activating Token Index: 984

Text #10

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5044. Min Act: -0.1700

Data Index: 7299415 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4971. Min Act: -0.1700

Data Index: 4485171 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5015. Min Act: -0.1700

Data Index: 5820803 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4815. Min Act: -0.1700

Data Index: 8083877 (Open Web Text)

Max Activating Token Index: 257

Text #14

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4953. Min Act: -0.1700

Data Index: 2924867 (Open Web Text)

Max Activating Token Index: 298

Text #15

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.5070. Min Act: -0.1700

Data Index: 14181 (Open Web Text)

Max Activating Token Index: 159

Text #16

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4882. Min Act: -0.1700

Data Index: 3850667 (Open Web Text)

Max Activating Token Index: 974

Text #17

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4990. Min Act: -0.1700

Data Index: 4542948 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4619. Min Act: -0.1700

Data Index: 2045415 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 3.5908. Min Range: -3.5908

Max Act: 3.4704. Min Act: -0.1700

Data Index: 8329622 (Open Web Text)

Max Activating Token Index: 354