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

Dataset: Open Web Text

Neuron 1552 in Layer 1

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: 3.6346. Min Range: -3.6346

Max Act: 3.6346. Min Act: -0.1700

Data Index: 2735676 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.6066. Min Act: -0.1700

Data Index: 3184611 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.5924. Min Act: -0.1700

Data Index: 7454052 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.5276. Min Act: -0.1700

Data Index: 6394763 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4866. Min Act: -0.1700

Data Index: 6602857 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.5058. Min Act: -0.1700

Data Index: 7454051 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4901. Min Act: -0.1700

Data Index: 4791739 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4756. Min Act: -0.1700

Data Index: 6788778 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4915. Min Act: -0.1700

Data Index: 925583 (Open Web Text)

Max Activating Token Index: 848

Text #9

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4622. Min Act: -0.1700

Data Index: 8820938 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4717. Min Act: -0.1700

Data Index: 522122 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4686. Min Act: -0.1700

Data Index: 7632834 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4435. Min Act: -0.1700

Data Index: 5845402 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4514. Min Act: -0.1700

Data Index: 5845404 (Open Web Text)

Max Activating Token Index: 173

Text #14

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4424. Min Act: -0.1700

Data Index: 7815677 (Open Web Text)

Max Activating Token Index: 514

Text #15

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4580. Min Act: -0.1700

Data Index: 3025585 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4488. Min Act: -0.1700

Data Index: 8486202 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4386. Min Act: -0.1700

Data Index: 357126 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4438. Min Act: -0.1700

Data Index: 5825622 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 3.6346. Min Range: -3.6346

Max Act: 3.4137. Min Act: -0.1700

Data Index: 8031906 (Open Web Text)

Max Activating Token Index: 597