Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.6591. Min Act: -0.1700
Data Index: 4784585 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.6279. Min Act: -0.1700
Data Index: 8147817 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.5029. Min Act: -0.1700
Data Index: 4123535 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.4404. Min Act: -0.1700
Data Index: 4225211 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.4091. Min Act: -0.1700
Data Index: 8214846 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.4091. Min Act: -0.1700
Data Index: 1790387 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.4091. Min Act: -0.1700
Data Index: 8036964 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.3779. Min Act: -0.1700
Data Index: 6502101 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 4123536 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 2732081 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 8626948 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2529. Min Act: -0.1700
Data Index: 1570183 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2841. Min Act: -0.1700
Data Index: 6502103 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2529. Min Act: -0.1700
Data Index: 7649005 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.2216. Min Act: -0.1700
Data Index: 5638628 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.1904. Min Act: -0.1700
Data Index: 3005124 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.1904. Min Act: -0.1700
Data Index: 4784575 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.1591. Min Act: -0.1700
Data Index: 7237100 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.1591. Min Act: -0.1700
Data Index: 6812475 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6591. Min Range: -5.6591
Max Act: 5.1279. Min Act: -0.1700
Data Index: 3214432 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19