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

Dataset: Open Web Text

Neuron 1441 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: 3.9975. Min Range: -3.9975

Max Act: 3.9975. Min Act: -0.1700

Data Index: 569679 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9340. Min Act: -0.1700

Data Index: 5085959 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8789. Min Act: -0.1700

Data Index: 2713143 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9304. Min Act: -0.1700

Data Index: 4204545 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8318. Min Act: -0.1700

Data Index: 6734642 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8187. Min Act: -0.1700

Data Index: 2376048 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7747. Min Act: -0.1700

Data Index: 3962577 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7549. Min Act: -0.1700

Data Index: 5625683 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7942. Min Act: -0.1700

Data Index: 2096551 (Open Web Text)

Max Activating Token Index: 806

Text #9

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7813. Min Act: -0.1700

Data Index: 5080147 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7740. Min Act: -0.1700

Data Index: 8771740 (Open Web Text)

Max Activating Token Index: 172

Text #11

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7709. Min Act: -0.1700

Data Index: 7412921 (Open Web Text)

Max Activating Token Index: 260

Text #12

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.7082. Min Act: -0.1700

Data Index: 5019856 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.6880. Min Act: -0.1700

Data Index: 2990659 (Open Web Text)

Max Activating Token Index: 331

Text #14

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.6466. Min Act: -0.1700

Data Index: 5017942 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.6130. Min Act: -0.1700

Data Index: 5244274 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.6415. Min Act: -0.1700

Data Index: 4207709 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.6593. Min Act: -0.1700

Data Index: 4299407 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.6011. Min Act: -0.1700

Data Index: 6997033 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.5884. Min Act: -0.1700

Data Index: 3401867 (Open Web Text)

Max Activating Token Index: 924