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

Dataset: Open Web Text

Neuron 1259 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: 4.6933. Min Range: -4.6933

Max Act: 4.6933. Min Act: -0.1700

Data Index: 2544010 (Open Web Text)

Max Activating Token Index: 703

Text #1

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.5496. Min Act: -0.1700

Data Index: 3092425 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.5502. Min Act: -0.1700

Data Index: 6931627 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.5239. Min Act: -0.1700

Data Index: 4346283 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.5433. Min Act: -0.1700

Data Index: 7109319 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.5198. Min Act: -0.1700

Data Index: 2519389 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.5218. Min Act: -0.1700

Data Index: 7021081 (Open Web Text)

Max Activating Token Index: 828

Text #7

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4681. Min Act: -0.1700

Data Index: 6866570 (Open Web Text)

Max Activating Token Index: 200

Text #8

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4956. Min Act: -0.1700

Data Index: 4443133 (Open Web Text)

Max Activating Token Index: 686

Text #9

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4888. Min Act: -0.1700

Data Index: 4869691 (Open Web Text)

Max Activating Token Index: 80

Text #10

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4924. Min Act: -0.1700

Data Index: 3501123 (Open Web Text)

Max Activating Token Index: 918

Text #11

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4955. Min Act: -0.1700

Data Index: 5434281 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4857. Min Act: -0.1700

Data Index: 1227191 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4785. Min Act: -0.1700

Data Index: 6891563 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4582. Min Act: -0.1700

Data Index: 3796410 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4101. Min Act: -0.1700

Data Index: 3447833 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4523. Min Act: -0.1700

Data Index: 3963648 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4220. Min Act: -0.1700

Data Index: 6670864 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4392. Min Act: -0.1700

Data Index: 6505997 (Open Web Text)

Max Activating Token Index: 430

Text #19

Max Range: 4.6933. Min Range: -4.6933

Max Act: 4.4238. Min Act: -0.1700

Data Index: 5900179 (Open Web Text)

Max Activating Token Index: 440