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

Dataset: Open Web Text

Neuron 2372 in Layer 2

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: 4.6255. Min Range: -4.6255

Max Act: 4.6123. Min Act: -0.1700

Data Index: 1614634 (Open Web Text)

Max Activating Token Index: 317

Text #1

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.6255. Min Act: -0.1700

Data Index: 2487770 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.6110. Min Act: -0.1700

Data Index: 4848503 (Open Web Text)

Max Activating Token Index: 99

Text #3

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5842. Min Act: -0.1700

Data Index: 1806490 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5411. Min Act: -0.1700

Data Index: 2005928 (Open Web Text)

Max Activating Token Index: 943

Text #5

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5308. Min Act: -0.1700

Data Index: 1529340 (Open Web Text)

Max Activating Token Index: 900

Text #6

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5464. Min Act: -0.1700

Data Index: 5619135 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5447. Min Act: -0.1700

Data Index: 8323954 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5056. Min Act: -0.1700

Data Index: 791840 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5331. Min Act: -0.1700

Data Index: 8420783 (Open Web Text)

Max Activating Token Index: 963

Text #10

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4764. Min Act: -0.1700

Data Index: 5939846 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5095. Min Act: -0.1700

Data Index: 8424213 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5003. Min Act: -0.1700

Data Index: 5710857 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4912. Min Act: -0.1700

Data Index: 4480564 (Open Web Text)

Max Activating Token Index: 97

Text #14

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.5096. Min Act: -0.1700

Data Index: 5983134 (Open Web Text)

Max Activating Token Index: 243

Text #15

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4595. Min Act: -0.1700

Data Index: 343421 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4575. Min Act: -0.1700

Data Index: 4218932 (Open Web Text)

Max Activating Token Index: 292

Text #17

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4011. Min Act: -0.1700

Data Index: 2929827 (Open Web Text)

Max Activating Token Index: 1019

Text #18

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4371. Min Act: -0.1700

Data Index: 3864233 (Open Web Text)

Max Activating Token Index: 525

Text #19

Max Range: 4.6255. Min Range: -4.6255

Max Act: 4.4458. Min Act: -0.1700

Data Index: 1168004 (Open Web Text)

Max Activating Token Index: 118