Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4295 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1363. Min Range: -6.1363
Max Act: 6.1363. Min Act: -0.1700
Data Index: 5789292 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1363. Min Range: -6.1363
Max Act: 6.0113. Min Act: -0.1700
Data Index: 1353191 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9800. Min Act: -0.1700
Data Index: 1244213 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9800. Min Act: -0.1700
Data Index: 584772 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9800. Min Act: -0.1700
Data Index: 1395208 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9488. Min Act: -0.1700
Data Index: 3463915 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9175. Min Act: -0.1700
Data Index: 7870450 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9175. Min Act: -0.1700
Data Index: 8585752 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9175. Min Act: -0.1699
Data Index: 7594061 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9175. Min Act: -0.1700
Data Index: 2285368 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.9175. Min Act: -0.1700
Data Index: 5034472 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8863. Min Act: -0.1700
Data Index: 5989115 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8863. Min Act: -0.1700
Data Index: 5185748 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8863. Min Act: -0.1700
Data Index: 4585554 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8863. Min Act: -0.1700
Data Index: 1012008 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8863. Min Act: -0.1700
Data Index: 3123548 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8550. Min Act: -0.1700
Data Index: 1270030 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8238. Min Act: -0.1700
Data Index: 4450183 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8550. Min Act: -0.1700
Data Index: 5473668 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1363. Min Range: -6.1363
Max Act: 5.8550. Min Act: -0.1700
Data Index: 2491957 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19