Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5595 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1961. Min Range: -6.1961
Max Act: 6.1961. Min Act: -0.1700
Data Index: 2093383 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1961. Min Range: -6.1961
Max Act: 6.0711. Min Act: -0.1700
Data Index: 2295325 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1961. Min Range: -6.1961
Max Act: 6.0399. Min Act: -0.1700
Data Index: 7986846 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1961. Min Range: -6.1961
Max Act: 6.0399. Min Act: -0.1700
Data Index: 7634554 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.9461. Min Act: -0.1700
Data Index: 4643168 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.9149. Min Act: -0.1700
Data Index: 4093283 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.8836. Min Act: -0.1700
Data Index: 7716108 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.8211. Min Act: -0.1700
Data Index: 5186890 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.8211. Min Act: -0.1700
Data Index: 1048246 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.7899. Min Act: -0.1700
Data Index: 7060000 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.7586. Min Act: -0.1700
Data Index: 4013277 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.7586. Min Act: -0.1700
Data Index: 6157847 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.7586. Min Act: -0.1700
Data Index: 7115972 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.7274. Min Act: -0.1700
Data Index: 6098692 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.7274. Min Act: -0.1700
Data Index: 7281649 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.6961. Min Act: -0.1700
Data Index: 3219072 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.6961. Min Act: -0.1700
Data Index: 8631100 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.6961. Min Act: -0.1700
Data Index: 6552459 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.6961. Min Act: -0.1700
Data Index: 5841904 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1961. Min Range: -6.1961
Max Act: 5.6961. Min Act: -0.1700
Data Index: 4293151 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19