Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.5390. Min Act: -0.1700
Data Index: 661203 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.5390. Min Act: -0.1700
Data Index: 4912618 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.3827. Min Act: -0.1700
Data Index: 138846 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.3202. Min Act: -0.1700
Data Index: 3151002 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.2577. Min Act: -0.1700
Data Index: 4214560 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.1952. Min Act: -0.1700
Data Index: 2777927 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.1952. Min Act: -0.1700
Data Index: 6888609 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.1640. Min Act: -0.1700
Data Index: 3644620 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.0702. Min Act: -0.1700
Data Index: 4046467 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.0702. Min Act: -0.1700
Data Index: 7157035 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.0077. Min Act: -0.1700
Data Index: 4625146 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.0390. Min Act: -0.1700
Data Index: 7466850 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1462142 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5390. Min Range: -6.5390
Max Act: 5.9452. Min Act: -0.1700
Data Index: 2445060 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5390. Min Range: -6.5390
Max Act: 5.9765. Min Act: -0.1700
Data Index: 2775130 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5390. Min Range: -6.5390
Max Act: 5.9765. Min Act: -0.1700
Data Index: 8534241 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5390. Min Range: -6.5390
Max Act: 6.0077. Min Act: -0.1700
Data Index: 4497051 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5390. Min Range: -6.5390
Max Act: 5.9765. Min Act: -0.1700
Data Index: 7085907 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5390. Min Range: -6.5390
Max Act: 5.9765. Min Act: -0.1700
Data Index: 3397909 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5390. Min Range: -6.5390
Max Act: 5.9765. Min Act: -0.1700
Data Index: 449381 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19