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

Dataset: Open Web Text

Neuron 939 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: 3.7371. Min Range: -3.7371

Max Act: 3.7371. Min Act: -0.1700

Data Index: 3164840 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.5911. Min Act: -0.1700

Data Index: 3193313 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3999. Min Act: -0.1700

Data Index: 7924882 (Open Web Text)

Max Activating Token Index: 71

Text #3

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.4161. Min Act: -0.1700

Data Index: 4797636 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3575. Min Act: -0.1700

Data Index: 8602476 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3610. Min Act: -0.1700

Data Index: 4080566 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3540. Min Act: -0.1700

Data Index: 5219652 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3161. Min Act: -0.1700

Data Index: 8815154 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3379. Min Act: -0.1700

Data Index: 3383231 (Open Web Text)

Max Activating Token Index: 151

Text #9

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.3173. Min Act: -0.1700

Data Index: 2129731 (Open Web Text)

Max Activating Token Index: 171

Text #10

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2671. Min Act: -0.1700

Data Index: 6132477 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2571. Min Act: -0.1700

Data Index: 2151486 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2641. Min Act: -0.1700

Data Index: 3014176 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2443. Min Act: -0.1700

Data Index: 5166541 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2847. Min Act: -0.1700

Data Index: 34743 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2264. Min Act: -0.1700

Data Index: 6520677 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.1887. Min Act: -0.1700

Data Index: 34006 (Open Web Text)

Max Activating Token Index: 1018

Text #17

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.2262. Min Act: -0.1700

Data Index: 4691926 (Open Web Text)

Max Activating Token Index: 46

Text #18

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.1932. Min Act: -0.1700

Data Index: 7584749 (Open Web Text)

Max Activating Token Index: 755

Text #19

Max Range: 3.7371. Min Range: -3.7371

Max Act: 3.1959. Min Act: -0.1700

Data Index: 6080594 (Open Web Text)

Max Activating Token Index: 654