Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3842 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.2644. Min Act: -0.1700
Data Index: 3579322 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.2644. Min Act: -0.1700
Data Index: 7915337 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.2019. Min Act: -0.1700
Data Index: 3257932 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.2019. Min Act: -0.1700
Data Index: 8230318 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.2019. Min Act: -0.1700
Data Index: 4549727 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.2019. Min Act: -0.1700
Data Index: 5471141 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1707. Min Act: -0.1700
Data Index: 453415 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1394. Min Act: -0.1700
Data Index: 6930622 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1707. Min Act: -0.1700
Data Index: 647355 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1394. Min Act: -0.1700
Data Index: 4263051 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1394. Min Act: -0.1700
Data Index: 7514099 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1394. Min Act: -0.1700
Data Index: 3122796 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1394. Min Act: -0.1700
Data Index: 203464 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.0769. Min Act: -0.1700
Data Index: 4425874 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1081. Min Act: -0.1700
Data Index: 70451 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.0769. Min Act: -0.1700
Data Index: 7361575 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1081. Min Act: -0.1700
Data Index: 6213163 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.1081. Min Act: -0.1700
Data Index: 5697429 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.0769. Min Act: -0.1700
Data Index: 190936 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2644. Min Range: -4.2644
Max Act: 4.0456. Min Act: -0.1700
Data Index: 6115992 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19