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

Dataset: Open Web Text

Neuron 1865 in Layer 4

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: 3.7218. Min Range: -3.7218

Max Act: 3.7218. Min Act: -0.1700

Data Index: 5443978 (Open Web Text)

Max Activating Token Index: 921

Text #1

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5992. Min Act: -0.1700

Data Index: 3367503 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.6202. Min Act: -0.1700

Data Index: 7887584 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5950. Min Act: -0.1700

Data Index: 8265233 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5907. Min Act: -0.1700

Data Index: 1808139 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5950. Min Act: -0.1700

Data Index: 5048823 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.6178. Min Act: -0.1700

Data Index: 3931353 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.6096. Min Act: -0.1700

Data Index: 2487368 (Open Web Text)

Max Activating Token Index: 999

Text #8

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.6035. Min Act: -0.1700

Data Index: 6413930 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5918. Min Act: -0.1700

Data Index: 5993760 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5968. Min Act: -0.1700

Data Index: 8664405 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5886. Min Act: -0.1700

Data Index: 5643855 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5797. Min Act: -0.1700

Data Index: 1089296 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5760. Min Act: -0.1700

Data Index: 3051632 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5724. Min Act: -0.1700

Data Index: 8036029 (Open Web Text)

Max Activating Token Index: 551

Text #15

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5796. Min Act: -0.1700

Data Index: 1012640 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5870. Min Act: -0.1700

Data Index: 4350212 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5598. Min Act: -0.1700

Data Index: 7478226 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5489. Min Act: -0.1700

Data Index: 4962043 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 3.7218. Min Range: -3.7218

Max Act: 3.5457. Min Act: -0.1700

Data Index: 1002480 (Open Web Text)

Max Activating Token Index: 678