Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5072 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3712. Min Range: -7.3712
Max Act: 7.3712. Min Act: -0.1700
Data Index: 4753418 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.9024. Min Act: -0.1700
Data Index: 2963413 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.8712. Min Act: -0.1700
Data Index: 8585369 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.4649. Min Act: -0.1700
Data Index: 2814882 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.4649. Min Act: -0.1700
Data Index: 470220 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.4024. Min Act: -0.1700
Data Index: 6184353 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.3712. Min Act: -0.1700
Data Index: 5065856 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.3712. Min Act: -0.1700
Data Index: 8814338 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.3712. Min Act: -0.1700
Data Index: 8392110 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.3399. Min Act: -0.1699
Data Index: 4590184 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2774. Min Act: -0.1700
Data Index: 3589758 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2774. Min Act: -0.1700
Data Index: 3881473 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2774. Min Act: -0.1700
Data Index: 5774826 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2774. Min Act: -0.1700
Data Index: 5180273 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2149. Min Act: -0.1700
Data Index: 1127766 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2462. Min Act: -0.1700
Data Index: 6869019 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2149. Min Act: -0.1700
Data Index: 1983002 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.2149. Min Act: -0.1700
Data Index: 5858163 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.1837. Min Act: -0.1700
Data Index: 7671105 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3712. Min Range: -7.3712
Max Act: 6.1524. Min Act: -0.1700
Data Index: 3500581 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19