Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1719 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1594. Min Range: -8.1594
Max Act: 8.1594. Min Act: -0.1700
Data Index: 4480191 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1594. Min Range: -8.1594
Max Act: 8.0969. Min Act: -0.1700
Data Index: 2166051 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9719. Min Act: -0.1700
Data Index: 1156854 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9719. Min Act: -0.1700
Data Index: 1266658 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9094. Min Act: -0.1700
Data Index: 2473128 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9094. Min Act: -0.1700
Data Index: 5374955 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9094. Min Act: -0.1700
Data Index: 7552193 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9094. Min Act: -0.1700
Data Index: 2375560 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.9094. Min Act: -0.1700
Data Index: 1727862 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.8469. Min Act: -0.1700
Data Index: 402876 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.8469. Min Act: -0.1700
Data Index: 1382337 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7844. Min Act: -0.1700
Data Index: 14151 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7844. Min Act: -0.1700
Data Index: 5956903 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7844. Min Act: -0.1700
Data Index: 5626486 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7844. Min Act: -0.1700
Data Index: 2197290 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7844. Min Act: -0.1700
Data Index: 4218584 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7844. Min Act: -0.1700
Data Index: 7795143 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7219. Min Act: -0.1700
Data Index: 6422060 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7219. Min Act: -0.1700
Data Index: 195554 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1594. Min Range: -8.1594
Max Act: 7.7219. Min Act: -0.1700
Data Index: 4568500 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19