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

Dataset: Open Web Text

Neuron 1293 in Layer 2

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: 1.8856. Min Range: -1.8856

Max Act: 1.8856. Min Act: -0.1700

Data Index: 2180441 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.8639. Min Act: -0.1700

Data Index: 5541337 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.8250. Min Act: -0.1700

Data Index: 6826813 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.8366. Min Act: -0.1700

Data Index: 6826812 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.8208. Min Act: -0.1700

Data Index: 4455787 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.8067. Min Act: -0.1700

Data Index: 6826818 (Open Web Text)

Max Activating Token Index: 818

Text #6

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7983. Min Act: -0.1700

Data Index: 6826815 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7905. Min Act: -0.1700

Data Index: 6826809 (Open Web Text)

Max Activating Token Index: 63

Text #8

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7868. Min Act: -0.1700

Data Index: 8088450 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7722. Min Act: -0.1700

Data Index: 6420818 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7665. Min Act: -0.1699

Data Index: 6711135 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7760. Min Act: -0.1700

Data Index: 2783214 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7489. Min Act: -0.1700

Data Index: 4743978 (Open Web Text)

Max Activating Token Index: 127

Text #13

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7595. Min Act: -0.1700

Data Index: 8067042 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7423. Min Act: -0.1700

Data Index: 6423080 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7354. Min Act: -0.1700

Data Index: 4502342 (Open Web Text)

Max Activating Token Index: 657

Text #16

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7535. Min Act: -0.1700

Data Index: 6301288 (Open Web Text)

Max Activating Token Index: 770

Text #17

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7513. Min Act: -0.1700

Data Index: 6826819 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7424. Min Act: -0.1700

Data Index: 3041115 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 1.8856. Min Range: -1.8856

Max Act: 1.7421. Min Act: -0.1700

Data Index: 6826811 (Open Web Text)

Max Activating Token Index: 628