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

Dataset: Open Web Text

Neuron 1094 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: 4.8282. Min Range: -4.8282

Max Act: 4.8282. Min Act: -0.1700

Data Index: 5892834 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.7342. Min Act: -0.1700

Data Index: 1998350 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6943. Min Act: -0.1700

Data Index: 1213037 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.7182. Min Act: -0.1700

Data Index: 2517694 (Open Web Text)

Max Activating Token Index: 876

Text #4

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6838. Min Act: -0.1700

Data Index: 5099725 (Open Web Text)

Max Activating Token Index: 822

Text #5

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.7169. Min Act: -0.1700

Data Index: 3637250 (Open Web Text)

Max Activating Token Index: 1003

Text #6

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.7011. Min Act: -0.1700

Data Index: 262990 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6553. Min Act: -0.1700

Data Index: 4072212 (Open Web Text)

Max Activating Token Index: 862

Text #8

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6333. Min Act: -0.1700

Data Index: 534500 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6301. Min Act: -0.1700

Data Index: 7762162 (Open Web Text)

Max Activating Token Index: 584

Text #10

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6309. Min Act: -0.1700

Data Index: 8045452 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6201. Min Act: -0.1700

Data Index: 2717497 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.5804. Min Act: -0.1700

Data Index: 6460501 (Open Web Text)

Max Activating Token Index: 989

Text #13

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.5835. Min Act: -0.1700

Data Index: 3975338 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6154. Min Act: -0.1700

Data Index: 17841 (Open Web Text)

Max Activating Token Index: 121

Text #15

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.5996. Min Act: -0.1700

Data Index: 8090498 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.6539. Min Act: -0.1700

Data Index: 1984706 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.5892. Min Act: -0.1700

Data Index: 3718297 (Open Web Text)

Max Activating Token Index: 837

Text #18

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.5829. Min Act: -0.1700

Data Index: 5448684 (Open Web Text)

Max Activating Token Index: 452

Text #19

Max Range: 4.8282. Min Range: -4.8282

Max Act: 4.5881. Min Act: -0.1700

Data Index: 1580733 (Open Web Text)

Max Activating Token Index: 434