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

Dataset: Open Web Text

Neuron 343 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: 4.2185. Min Range: -4.2185

Max Act: 4.2185. Min Act: -0.1700

Data Index: 2586272 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1791. Min Act: -0.1700

Data Index: 6885465 (Open Web Text)

Max Activating Token Index: 207

Text #2

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.2133. Min Act: -0.1700

Data Index: 5998885 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1828. Min Act: -0.1700

Data Index: 7175611 (Open Web Text)

Max Activating Token Index: 531

Text #4

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1765. Min Act: -0.1700

Data Index: 2202248 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1287. Min Act: -0.1700

Data Index: 4640281 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1331. Min Act: -0.1700

Data Index: 3051132 (Open Web Text)

Max Activating Token Index: 515

Text #7

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1319. Min Act: -0.1700

Data Index: 5319257 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1234. Min Act: -0.1700

Data Index: 5534340 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1173. Min Act: -0.1700

Data Index: 6173829 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1457. Min Act: -0.1700

Data Index: 4564955 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.0927. Min Act: -0.1700

Data Index: 6528790 (Open Web Text)

Max Activating Token Index: 532

Text #12

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1100. Min Act: -0.1700

Data Index: 1261463 (Open Web Text)

Max Activating Token Index: 234

Text #13

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1079. Min Act: -0.1700

Data Index: 4632777 (Open Web Text)

Max Activating Token Index: 611

Text #14

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1050. Min Act: -0.1700

Data Index: 4080746 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1003. Min Act: -0.1700

Data Index: 6208750 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1169. Min Act: -0.1700

Data Index: 3357363 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.0950. Min Act: -0.1700

Data Index: 263797 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.0916. Min Act: -0.1700

Data Index: 5061694 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 4.2185. Min Range: -4.2185

Max Act: 4.1089. Min Act: -0.1700

Data Index: 4871363 (Open Web Text)

Max Activating Token Index: 433