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

Dataset: Open Web Text

Neuron 2477 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: 3.6183. Min Range: -3.6183

Max Act: 3.6183. Min Act: -0.1700

Data Index: 8438778 (Open Web Text)

Max Activating Token Index: 189

Text #1

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.5350. Min Act: -0.1700

Data Index: 780813 (Open Web Text)

Max Activating Token Index: 100

Text #2

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4907. Min Act: -0.1700

Data Index: 7749465 (Open Web Text)

Max Activating Token Index: 793

Text #3

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4555. Min Act: -0.1700

Data Index: 2062211 (Open Web Text)

Max Activating Token Index: 924

Text #4

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4188. Min Act: -0.1700

Data Index: 4480642 (Open Web Text)

Max Activating Token Index: 223

Text #5

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1014780 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3998. Min Act: -0.1700

Data Index: 8669597 (Open Web Text)

Max Activating Token Index: 573

Text #7

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4305. Min Act: -0.1700

Data Index: 1163505 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4137. Min Act: -0.1700

Data Index: 3122927 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.4034. Min Act: -0.1700

Data Index: 2660646 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3731. Min Act: -0.1700

Data Index: 2651756 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3478. Min Act: -0.1700

Data Index: 2092899 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3641. Min Act: -0.1700

Data Index: 3006467 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3703. Min Act: -0.1700

Data Index: 6271178 (Open Web Text)

Max Activating Token Index: 213

Text #14

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3480. Min Act: -0.1700

Data Index: 221610 (Open Web Text)

Max Activating Token Index: 636

Text #15

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3579. Min Act: -0.1700

Data Index: 7337942 (Open Web Text)

Max Activating Token Index: 325

Text #16

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3214. Min Act: -0.1700

Data Index: 4540010 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3320. Min Act: -0.1700

Data Index: 2182799 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3196. Min Act: -0.1700

Data Index: 6068582 (Open Web Text)

Max Activating Token Index: 183

Text #19

Max Range: 3.6183. Min Range: -3.6183

Max Act: 3.3354. Min Act: -0.1700

Data Index: 6106025 (Open Web Text)

Max Activating Token Index: 240