Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4240 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.9900. Min Act: -0.1700
Data Index: 5618027 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.9900. Min Act: -0.1700
Data Index: 5820644 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.6775. Min Act: -0.1700
Data Index: 3758688 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.6775. Min Act: -0.1700
Data Index: 5722460 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.6150. Min Act: -0.1700
Data Index: 5109600 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.6150. Min Act: -0.1700
Data Index: 4785292 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.5525. Min Act: -0.1700
Data Index: 6871024 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.3650. Min Act: -0.1700
Data Index: 2231210 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.3025. Min Act: -0.1700
Data Index: 7051562 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.3025. Min Act: -0.1700
Data Index: 1442563 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.2400. Min Act: -0.1700
Data Index: 480729 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1462. Min Act: -0.1700
Data Index: 8302839 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1775. Min Act: -0.1700
Data Index: 8575395 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1775. Min Act: -0.1700
Data Index: 6165527 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 2652904 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1150. Min Act: -0.1700
Data Index: 8154357 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.1462. Min Act: -0.1700
Data Index: 1366186 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.0837. Min Act: -0.1700
Data Index: 2727395 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.0837. Min Act: -0.1700
Data Index: 2424889 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9900. Min Range: -8.9900
Max Act: 8.0525. Min Act: -0.1700
Data Index: 4291865 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19