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

Dataset: Open Web Text

Neuron 1118 in Layer 6

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: 5.9181. Min Range: -5.9181

Max Act: 5.9181. Min Act: -0.1700

Data Index: 7706155 (Open Web Text)

Max Activating Token Index: 478

Text #1

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.8752. Min Act: -0.1700

Data Index: 5039172 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7826. Min Act: -0.1700

Data Index: 4324912 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7723. Min Act: -0.1700

Data Index: 5884053 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.8109. Min Act: -0.1700

Data Index: 297632 (Open Web Text)

Max Activating Token Index: 681

Text #5

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7907. Min Act: -0.1700

Data Index: 4324913 (Open Web Text)

Max Activating Token Index: 759

Text #6

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.8071. Min Act: -0.1700

Data Index: 4567355 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7709. Min Act: -0.1700

Data Index: 7673241 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7435. Min Act: -0.1700

Data Index: 7980370 (Open Web Text)

Max Activating Token Index: 499

Text #9

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7281. Min Act: -0.1700

Data Index: 6896201 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7673. Min Act: -0.1700

Data Index: 8501899 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7555. Min Act: -0.1700

Data Index: 351786 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7753. Min Act: -0.1700

Data Index: 5056127 (Open Web Text)

Max Activating Token Index: 498

Text #13

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7391. Min Act: -0.1700

Data Index: 5056126 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7368. Min Act: -0.1700

Data Index: 1987819 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7009. Min Act: -0.1700

Data Index: 143142 (Open Web Text)

Max Activating Token Index: 904

Text #16

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.6856. Min Act: -0.1700

Data Index: 7954791 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.7118. Min Act: -0.1700

Data Index: 8634594 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.6908. Min Act: -0.1700

Data Index: 3143900 (Open Web Text)

Max Activating Token Index: 995

Text #19

Max Range: 5.9181. Min Range: -5.9181

Max Act: 5.6761. Min Act: -0.1700

Data Index: 3315436 (Open Web Text)

Max Activating Token Index: 697