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

Dataset: Open Web Text

Neuron 660 in Layer 2

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: 1.6843. Min Range: -1.6843

Max Act: 1.6843. Min Act: -0.1700

Data Index: 4836962 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.6298. Min Act: -0.1700

Data Index: 1808082 (Open Web Text)

Max Activating Token Index: 211

Text #2

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.6301. Min Act: -0.1700

Data Index: 3995398 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5996. Min Act: -0.1700

Data Index: 3736799 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5798. Min Act: -0.1700

Data Index: 3318303 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5797. Min Act: -0.1700

Data Index: 1202183 (Open Web Text)

Max Activating Token Index: 193

Text #6

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5918. Min Act: -0.1700

Data Index: 7626220 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5896. Min Act: -0.1700

Data Index: 3790480 (Open Web Text)

Max Activating Token Index: 68

Text #8

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5541. Min Act: -0.1700

Data Index: 2986136 (Open Web Text)

Max Activating Token Index: 317

Text #9

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5485. Min Act: -0.1700

Data Index: 2594590 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5398. Min Act: -0.1700

Data Index: 3045316 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5426. Min Act: -0.1700

Data Index: 1105369 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5229. Min Act: -0.1700

Data Index: 2740427 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5215. Min Act: -0.1700

Data Index: 100306 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5336. Min Act: -0.1700

Data Index: 7856233 (Open Web Text)

Max Activating Token Index: 91

Text #15

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5279. Min Act: -0.1700

Data Index: 4015250 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5272. Min Act: -0.1700

Data Index: 5684546 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5090. Min Act: -0.1700

Data Index: 1427087 (Open Web Text)

Max Activating Token Index: 57

Text #18

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.5120. Min Act: -0.1700

Data Index: 8643120 (Open Web Text)

Max Activating Token Index: 67

Text #19

Max Range: 1.6843. Min Range: -1.6843

Max Act: 1.4943. Min Act: -0.1700

Data Index: 4439220 (Open Web Text)

Max Activating Token Index: 123