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

Dataset: Open Web Text

Neuron 741 in Layer 3

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: 4.7225. Min Range: -4.7225

Max Act: 4.7225. Min Act: -0.1700

Data Index: 5556761 (Open Web Text)

Max Activating Token Index: 902

Text #1

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.6290. Min Act: -0.1700

Data Index: 615873 (Open Web Text)

Max Activating Token Index: 446

Text #2

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.6263. Min Act: -0.1700

Data Index: 3900831 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.6014. Min Act: -0.1700

Data Index: 8756061 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5782. Min Act: -0.1700

Data Index: 1246451 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5734. Min Act: -0.1700

Data Index: 8459528 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5874. Min Act: -0.1700

Data Index: 3203125 (Open Web Text)

Max Activating Token Index: 625

Text #7

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5221. Min Act: -0.1700

Data Index: 3203126 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5343. Min Act: -0.1700

Data Index: 1795856 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4964. Min Act: -0.1700

Data Index: 2318145 (Open Web Text)

Max Activating Token Index: 307

Text #10

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4933. Min Act: -0.1700

Data Index: 6857560 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4760. Min Act: -0.1700

Data Index: 3892779 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4924. Min Act: -0.1700

Data Index: 3812454 (Open Web Text)

Max Activating Token Index: 862

Text #13

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4969. Min Act: -0.1700

Data Index: 3894410 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5105. Min Act: -0.1700

Data Index: 1525423 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.5263. Min Act: -0.1700

Data Index: 1713882 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4725. Min Act: -0.1700

Data Index: 8300442 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4866. Min Act: -0.1700

Data Index: 4051987 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4591. Min Act: -0.1700

Data Index: 8424107 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 4.7225. Min Range: -4.7225

Max Act: 4.4645. Min Act: -0.1700

Data Index: 5608890 (Open Web Text)

Max Activating Token Index: 259