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

Dataset: Open Web Text

Neuron 1837 in Layer 3

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: 4.2856. Min Range: -4.2856

Max Act: 4.2856. Min Act: -0.1700

Data Index: 5269404 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.2580. Min Act: -0.1700

Data Index: 5899608 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.2005. Min Act: -0.1700

Data Index: 4801799 (Open Web Text)

Max Activating Token Index: 783

Text #3

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.2041. Min Act: -0.1700

Data Index: 5269405 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.1162. Min Act: -0.1700

Data Index: 5440613 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.1146. Min Act: -0.1700

Data Index: 6111956 (Open Web Text)

Max Activating Token Index: 597

Text #6

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0888. Min Act: -0.1700

Data Index: 2611013 (Open Web Text)

Max Activating Token Index: 138

Text #7

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0378. Min Act: -0.1700

Data Index: 7708782 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0755. Min Act: -0.1700

Data Index: 7708778 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0241. Min Act: -0.1700

Data Index: 8337646 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0492. Min Act: -0.1700

Data Index: 2025291 (Open Web Text)

Max Activating Token Index: 648

Text #11

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0449. Min Act: -0.1700

Data Index: 6804100 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0150. Min Act: -0.1700

Data Index: 2832457 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0081. Min Act: -0.1700

Data Index: 4771428 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 4.2856. Min Range: -4.2856

Max Act: 3.9951. Min Act: -0.1700

Data Index: 6654260 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 4.2856. Min Range: -4.2856

Max Act: 3.9891. Min Act: -0.1700

Data Index: 731678 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 4.2856. Min Range: -4.2856

Max Act: 3.9442. Min Act: -0.1700

Data Index: 315114 (Open Web Text)

Max Activating Token Index: 169

Text #17

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0330. Min Act: -0.1700

Data Index: 2905203 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 4.2856. Min Range: -4.2856

Max Act: 4.0038. Min Act: -0.1700

Data Index: 1128333 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 4.2856. Min Range: -4.2856

Max Act: 3.9506. Min Act: -0.1700

Data Index: 819433 (Open Web Text)

Max Activating Token Index: 370