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

Dataset: Open Web Text

Neuron 2868 in Layer 4

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: 4.4078. Min Range: -4.4078

Max Act: 4.3854. Min Act: -0.1700

Data Index: 4019361 (Open Web Text)

Max Activating Token Index: 239

Text #1

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.4078. Min Act: -0.1700

Data Index: 237569 (Open Web Text)

Max Activating Token Index: 532

Text #2

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.2988. Min Act: -0.1700

Data Index: 4560343 (Open Web Text)

Max Activating Token Index: 90

Text #3

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.3506. Min Act: -0.1700

Data Index: 4872428 (Open Web Text)

Max Activating Token Index: 296

Text #4

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.3287. Min Act: -0.1700

Data Index: 5185763 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.2774. Min Act: -0.1700

Data Index: 2283888 (Open Web Text)

Max Activating Token Index: 248

Text #6

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.2747. Min Act: -0.1700

Data Index: 5633897 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1485. Min Act: -0.1700

Data Index: 8586958 (Open Web Text)

Max Activating Token Index: 725

Text #8

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1928. Min Act: -0.1700

Data Index: 6114825 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.2020. Min Act: -0.1700

Data Index: 7555850 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1945. Min Act: -0.1700

Data Index: 3810650 (Open Web Text)

Max Activating Token Index: 816

Text #11

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1320. Min Act: -0.1700

Data Index: 3270938 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1866. Min Act: -0.1700

Data Index: 813214 (Open Web Text)

Max Activating Token Index: 887

Text #13

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1212. Min Act: -0.1700

Data Index: 3480290 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1061. Min Act: -0.1700

Data Index: 8707679 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1215. Min Act: -0.1700

Data Index: 4470220 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1251. Min Act: -0.1700

Data Index: 8791290 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1504. Min Act: -0.1700

Data Index: 4391898 (Open Web Text)

Max Activating Token Index: 136

Text #18

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1394. Min Act: -0.1700

Data Index: 4737282 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 4.4078. Min Range: -4.4078

Max Act: 4.1067. Min Act: -0.1700

Data Index: 7584004 (Open Web Text)

Max Activating Token Index: 406