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

Dataset: Open Web Text

Neuron 893 in Layer 4

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: 3.1549. Min Range: -3.1549

Max Act: 3.1549. Min Act: -0.1700

Data Index: 4226995 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.1027. Min Act: -0.1700

Data Index: 1071062 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.1021. Min Act: -0.1700

Data Index: 6013410 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.1021. Min Act: -0.1700

Data Index: 6107059 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0684. Min Act: -0.1700

Data Index: 1928811 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0765. Min Act: -0.1700

Data Index: 7327955 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0640. Min Act: -0.1700

Data Index: 3782624 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0632. Min Act: -0.1700

Data Index: 8601999 (Open Web Text)

Max Activating Token Index: 684

Text #8

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0632. Min Act: -0.1700

Data Index: 1544489 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0741. Min Act: -0.1700

Data Index: 410701 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0401. Min Act: -0.1700

Data Index: 6104800 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0388. Min Act: -0.1700

Data Index: 1602436 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0628. Min Act: -0.1700

Data Index: 5821565 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0480. Min Act: -0.1700

Data Index: 7708473 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0180. Min Act: -0.1700

Data Index: 3600080 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0279. Min Act: -0.1700

Data Index: 4765884 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0335. Min Act: -0.1700

Data Index: 1321121 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0222. Min Act: -0.1700

Data Index: 4190363 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0354. Min Act: -0.1700

Data Index: 6282108 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 3.1549. Min Range: -3.1549

Max Act: 3.0190. Min Act: -0.1700

Data Index: 6321412 (Open Web Text)

Max Activating Token Index: 85