Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0469. Min Range: -6.0469
Max Act: 6.0469. Min Act: -0.1700
Data Index: 8586545 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.8906. Min Act: -0.1700
Data Index: 8635265 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.8594. Min Act: -0.1700
Data Index: 5012520 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.8281. Min Act: -0.1700
Data Index: 8635264 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.7656. Min Act: -0.1700
Data Index: 2355107 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.7969. Min Act: -0.1700
Data Index: 2090468 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.7969. Min Act: -0.1700
Data Index: 4581809 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.7344. Min Act: -0.1700
Data Index: 2941041 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.7031. Min Act: -0.1700
Data Index: 5792220 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.7031. Min Act: -0.1700
Data Index: 8658068 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6719. Min Act: -0.1700
Data Index: 7049268 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6719. Min Act: -0.1700
Data Index: 5644060 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6719. Min Act: -0.1700
Data Index: 2871064 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6406. Min Act: -0.1700
Data Index: 2961528 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6406. Min Act: -0.1700
Data Index: 880307 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6719. Min Act: -0.1700
Data Index: 8541669 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6406. Min Act: -0.1700
Data Index: 6183571 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6406. Min Act: -0.1700
Data Index: 2986078 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.6406. Min Act: -0.1700
Data Index: 8541657 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0469. Min Range: -6.0469
Max Act: 5.5781. Min Act: -0.1700
Data Index: 3941278 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19