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

Dataset: Open Web Text

Neuron 2947 in Layer 0

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: 5.9541. Min Range: -5.9541

Max Act: 5.9541. Min Act: -0.1700

Data Index: 996740 (Open Web Text)

Max Activating Token Index: 53

Text #1

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.8204. Min Act: -0.1700

Data Index: 4797099 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.7204. Min Act: -0.1700

Data Index: 3895272 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.7031. Min Act: -0.1700

Data Index: 2527938 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5960. Min Act: -0.1700

Data Index: 3161778 (Open Web Text)

Max Activating Token Index: 959

Text #5

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.6329. Min Act: -0.1700

Data Index: 4510597 (Open Web Text)

Max Activating Token Index: 652

Text #6

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5867. Min Act: -0.1700

Data Index: 4847607 (Open Web Text)

Max Activating Token Index: 527

Text #7

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5717. Min Act: -0.1700

Data Index: 4983401 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5303. Min Act: -0.1700

Data Index: 358776 (Open Web Text)

Max Activating Token Index: 690

Text #9

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5069. Min Act: -0.1700

Data Index: 5643706 (Open Web Text)

Max Activating Token Index: 968

Text #10

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5349. Min Act: -0.1700

Data Index: 6016551 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5766. Min Act: -0.1700

Data Index: 7189490 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5250. Min Act: -0.1700

Data Index: 4434684 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.4882. Min Act: -0.1700

Data Index: 6401617 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.4930. Min Act: -0.1700

Data Index: 838839 (Open Web Text)

Max Activating Token Index: 663

Text #15

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5358. Min Act: -0.1700

Data Index: 7637280 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.4963. Min Act: -0.1700

Data Index: 2043249 (Open Web Text)

Max Activating Token Index: 807

Text #17

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.5338. Min Act: -0.1700

Data Index: 6182405 (Open Web Text)

Max Activating Token Index: 924

Text #18

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.4953. Min Act: -0.1700

Data Index: 996901 (Open Web Text)

Max Activating Token Index: 77

Text #19

Max Range: 5.9541. Min Range: -5.9541

Max Act: 5.4618. Min Act: -0.1700

Data Index: 1421042 (Open Web Text)

Max Activating Token Index: 232