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

Dataset: Open Web Text

Neuron 2652 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: 4.8521. Min Range: -4.8521

Max Act: 4.8521. Min Act: -0.1700

Data Index: 3736715 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.8092. Min Act: -0.1700

Data Index: 1507751 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7900. Min Act: -0.1700

Data Index: 6491580 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7723. Min Act: -0.1700

Data Index: 5910442 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7811. Min Act: -0.1700

Data Index: 5886348 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7757. Min Act: -0.1700

Data Index: 6534710 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7739. Min Act: -0.1700

Data Index: 3383042 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7782. Min Act: -0.1700

Data Index: 3127504 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7837. Min Act: -0.1700

Data Index: 1069995 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7409. Min Act: -0.1700

Data Index: 2023996 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7455. Min Act: -0.1700

Data Index: 8415832 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7686. Min Act: -0.1700

Data Index: 8754870 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7477. Min Act: -0.1700

Data Index: 4920528 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7189. Min Act: -0.1700

Data Index: 2073335 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7226. Min Act: -0.1700

Data Index: 4425848 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7127. Min Act: -0.1700

Data Index: 6162236 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7120. Min Act: -0.1700

Data Index: 6308595 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7145. Min Act: -0.1700

Data Index: 2908268 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7087. Min Act: -0.1700

Data Index: 2999332 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.8521. Min Range: -4.8521

Max Act: 4.7205. Min Act: -0.1700

Data Index: 925069 (Open Web Text)

Max Activating Token Index: 3