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

Dataset: Open Web Text

Neuron 158 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: 5.0173. Min Range: -5.0173

Max Act: 5.0173. Min Act: -0.1700

Data Index: 4411783 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.9959. Min Act: -0.1700

Data Index: 3009291 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.8770. Min Act: -0.1700

Data Index: 180378 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.8755. Min Act: -0.1700

Data Index: 4163672 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.8059. Min Act: -0.1700

Data Index: 3547056 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.8075. Min Act: -0.1700

Data Index: 4316335 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7979. Min Act: -0.1700

Data Index: 2022719 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7568. Min Act: -0.1700

Data Index: 402995 (Open Web Text)

Max Activating Token Index: 517

Text #8

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7755. Min Act: -0.1700

Data Index: 251822 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7644. Min Act: -0.1700

Data Index: 1935953 (Open Web Text)

Max Activating Token Index: 375

Text #10

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7542. Min Act: -0.1700

Data Index: 5277737 (Open Web Text)

Max Activating Token Index: 310

Text #11

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7316. Min Act: -0.1700

Data Index: 123482 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7284. Min Act: -0.1700

Data Index: 7519494 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7383. Min Act: -0.1700

Data Index: 7206748 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7148. Min Act: -0.1700

Data Index: 3288573 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.6752. Min Act: -0.1700

Data Index: 70173 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.6771. Min Act: -0.1700

Data Index: 871105 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.6950. Min Act: -0.1700

Data Index: 4242257 (Open Web Text)

Max Activating Token Index: 102

Text #18

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.7216. Min Act: -0.1699

Data Index: 876533 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 5.0173. Min Range: -5.0173

Max Act: 4.6937. Min Act: -0.1700

Data Index: 2962212 (Open Web Text)

Max Activating Token Index: 9