Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3694. Min Range: -8.3694
Max Act: 8.3694. Min Act: -0.1700
Data Index: 5962618 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3694. Min Range: -8.3694
Max Act: 8.1506. Min Act: -0.1700
Data Index: 7480523 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3694. Min Range: -8.3694
Max Act: 8.1506. Min Act: -0.1700
Data Index: 2406271 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.9944. Min Act: -0.1700
Data Index: 6410068 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.9319. Min Act: -0.1700
Data Index: 3188096 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.9319. Min Act: -0.1700
Data Index: 6131118 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.8694. Min Act: -0.1700
Data Index: 1148647 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.8694. Min Act: -0.1700
Data Index: 3777928 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.8694. Min Act: -0.1700
Data Index: 8153793 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.8694. Min Act: -0.1700
Data Index: 6509184 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.7756. Min Act: -0.1700
Data Index: 5602956 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5881. Min Act: -0.1700
Data Index: 5025020 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5881. Min Act: -0.1700
Data Index: 7330323 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5569. Min Act: -0.1700
Data Index: 8357760 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5569. Min Act: -0.1700
Data Index: 442627 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5881. Min Act: -0.1700
Data Index: 8658429 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5569. Min Act: -0.1700
Data Index: 765264 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5256. Min Act: -0.1700
Data Index: 4934126 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.4944. Min Act: -0.1700
Data Index: 621058 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3694. Min Range: -8.3694
Max Act: 7.5256. Min Act: -0.1700
Data Index: 4846757 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19