Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4439 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.5108. Min Act: -0.1700
Data Index: 1477079 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.4952. Min Act: -0.1700
Data Index: 6783558 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.4952. Min Act: -0.1700
Data Index: 604203 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.4639. Min Act: -0.1700
Data Index: 1072792 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.4639. Min Act: -0.1700
Data Index: 8445018 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.4012. Min Act: -0.1700
Data Index: 1477078 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.4012. Min Act: -0.1700
Data Index: 7041017 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3698. Min Act: -0.1700
Data Index: 7545875 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3698. Min Act: -0.1700
Data Index: 7110783 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3541. Min Act: -0.1700
Data Index: 8148726 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3384. Min Act: -0.1700
Data Index: 4629378 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3070. Min Act: -0.1700
Data Index: 8445017 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3070. Min Act: -0.1700
Data Index: 2408786 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3227. Min Act: -0.1700
Data Index: 5698178 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3070. Min Act: -0.1700
Data Index: 2024915 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3070. Min Act: -0.1700
Data Index: 2376499 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.3070. Min Act: -0.1700
Data Index: 8445016 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.2756. Min Act: -0.1700
Data Index: 5827097 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.2442. Min Act: -0.1700
Data Index: 8607467 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5108. Min Range: -3.5108
Max Act: 3.2285. Min Act: -0.1700
Data Index: 36748 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19