Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.1916. Min Act: -0.1700
Data Index: 2950825 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.1603. Min Act: -0.1700
Data Index: 7528693 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.1916. Min Act: -0.1700
Data Index: 7377233 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.1603. Min Act: -0.1700
Data Index: 1536125 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.0978. Min Act: -0.1700
Data Index: 124060 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.0665. Min Act: -0.1700
Data Index: 1791972 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.0040. Min Act: -0.1700
Data Index: 4768306 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.9728. Min Act: -0.1700
Data Index: 5149261 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1916. Min Range: -4.1916
Max Act: 4.0040. Min Act: -0.1700
Data Index: 8648728 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.9415. Min Act: -0.1700
Data Index: 1572204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.9102. Min Act: -0.1700
Data Index: 3034961 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.8790. Min Act: -0.1700
Data Index: 5113114 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.9102. Min Act: -0.1700
Data Index: 4258266 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.9102. Min Act: -0.1700
Data Index: 7343330 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.9102. Min Act: -0.1700
Data Index: 4939030 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.8790. Min Act: -0.1700
Data Index: 7526870 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.8790. Min Act: -0.1700
Data Index: 2100121 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.8790. Min Act: -0.1700
Data Index: 2322157 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.8790. Min Act: -0.1700
Data Index: 7163771 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1916. Min Range: -4.1916
Max Act: 3.8790. Min Act: -0.1700
Data Index: 5721460 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19