Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0478. Min Range: -2.0478
Max Act: 2.0478. Min Act: -0.1700
Data Index: 8401487 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0478. Min Range: -2.0478
Max Act: 2.0309. Min Act: -0.1700
Data Index: 7057247 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0478. Min Range: -2.0478
Max Act: 2.0141. Min Act: -0.1700
Data Index: 4955028 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9972. Min Act: -0.1700
Data Index: 7552686 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9972. Min Act: -0.1700
Data Index: 8374221 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9972. Min Act: -0.1700
Data Index: 7903262 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0478. Min Range: -2.0478
Max Act: 2.0141. Min Act: -0.1700
Data Index: 3458457 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9972. Min Act: -0.1700
Data Index: 3290903 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 963308 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 422339 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 493169 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9972. Min Act: -0.1700
Data Index: 8722614 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 5449652 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 5122853 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 8601049 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9803. Min Act: -0.1700
Data Index: 7180979 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9718. Min Act: -0.1700
Data Index: 1333654 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9718. Min Act: -0.1700
Data Index: 6946531 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9718. Min Act: -0.1700
Data Index: 7995593 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0478. Min Range: -2.0478
Max Act: 1.9718. Min Act: -0.1700
Data Index: 478017 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19