Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.9783. Min Act: -0.1700
Data Index: 7858072 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.8533. Min Act: -0.1700
Data Index: 2396900 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.8220. Min Act: -0.1700
Data Index: 8049179 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.8220. Min Act: -0.1700
Data Index: 153409 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.8533. Min Act: -0.1700
Data Index: 501148 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.7595. Min Act: -0.1700
Data Index: 2862070 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.7283. Min Act: -0.1700
Data Index: 4349885 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6970. Min Act: -0.1700
Data Index: 97946 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6970. Min Act: -0.1700
Data Index: 4133723 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6970. Min Act: -0.1700
Data Index: 8044750 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6658. Min Act: -0.1700
Data Index: 6007530 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6658. Min Act: -0.1700
Data Index: 1000663 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6658. Min Act: -0.1700
Data Index: 978500 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6345. Min Act: -0.1700
Data Index: 4030084 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6345. Min Act: -0.1700
Data Index: 8228879 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6345. Min Act: -0.1700
Data Index: 2913975 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6345. Min Act: -0.1700
Data Index: 3256871 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6033. Min Act: -0.1700
Data Index: 548884 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6033. Min Act: -0.1700
Data Index: 4632930 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9783. Min Range: -4.9783
Max Act: 4.6033. Min Act: -0.1700
Data Index: 4312891 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19