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

Dataset: Open Web Text

Neuron 1411 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: 6.6190. Min Range: -6.6190

Max Act: 6.5695. Min Act: -0.1700

Data Index: 3453356 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5552. Min Act: -0.1700

Data Index: 6847293 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.6190. Min Act: -0.1700

Data Index: 578619 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5639. Min Act: -0.1700

Data Index: 1192449 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5389. Min Act: -0.1700

Data Index: 2580045 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5675. Min Act: -0.1700

Data Index: 3571493 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5286. Min Act: -0.1700

Data Index: 6043710 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5304. Min Act: -0.1700

Data Index: 2075717 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5042. Min Act: -0.1700

Data Index: 3595793 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5475. Min Act: -0.1700

Data Index: 5179175 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5286. Min Act: -0.1700

Data Index: 2203836 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5103. Min Act: -0.1700

Data Index: 4062200 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.5164. Min Act: -0.1700

Data Index: 420427 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4582. Min Act: -0.1700

Data Index: 7647199 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4584. Min Act: -0.1700

Data Index: 8567854 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4719. Min Act: -0.1700

Data Index: 6229019 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4540. Min Act: -0.1700

Data Index: 6895077 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4471. Min Act: -0.1700

Data Index: 1887759 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4582. Min Act: -0.1700

Data Index: 5759360 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 6.6190. Min Range: -6.6190

Max Act: 6.4582. Min Act: -0.1700

Data Index: 6056383 (Open Web Text)

Max Activating Token Index: 3