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

Dataset: Open Web Text

Neuron 2350 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: 4.5629. Min Range: -4.5629

Max Act: 4.5418. Min Act: -0.1700

Data Index: 4423591 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4961. Min Act: -0.1700

Data Index: 3925195 (Open Web Text)

Max Activating Token Index: 613

Text #2

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.5629. Min Act: -0.1700

Data Index: 4925667 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.5044. Min Act: -0.1700

Data Index: 2843727 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4358. Min Act: -0.1700

Data Index: 4540413 (Open Web Text)

Max Activating Token Index: 405

Text #5

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4630. Min Act: -0.1700

Data Index: 1383028 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4539. Min Act: -0.1700

Data Index: 2205684 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4560. Min Act: -0.1700

Data Index: 6921089 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.3968. Min Act: -0.1700

Data Index: 6834604 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4055. Min Act: -0.1700

Data Index: 5033229 (Open Web Text)

Max Activating Token Index: 450

Text #10

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4439. Min Act: -0.1700

Data Index: 8591165 (Open Web Text)

Max Activating Token Index: 955

Text #11

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4237. Min Act: -0.1700

Data Index: 8687324 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4297. Min Act: -0.1700

Data Index: 5178693 (Open Web Text)

Max Activating Token Index: 482

Text #13

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4251. Min Act: -0.1700

Data Index: 3913176 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.3986. Min Act: -0.1700

Data Index: 3263936 (Open Web Text)

Max Activating Token Index: 732

Text #15

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.3818. Min Act: -0.1700

Data Index: 7175725 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.4056. Min Act: -0.1700

Data Index: 6057718 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.3612. Min Act: -0.1700

Data Index: 6046133 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.3128. Min Act: -0.1700

Data Index: 5460459 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 4.5629. Min Range: -4.5629

Max Act: 4.3543. Min Act: -0.1700

Data Index: 8481930 (Open Web Text)

Max Activating Token Index: 667