Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 919 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.9170. Min Act: -0.1700
Data Index: 2531576 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.8857. Min Act: -0.1700
Data Index: 8129890 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.8545. Min Act: -0.1700
Data Index: 6574148 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.7607. Min Act: -0.1700
Data Index: 4280993 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 5828296 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.7920. Min Act: -0.1700
Data Index: 5965175 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.7295. Min Act: -0.1700
Data Index: 7199707 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.6982. Min Act: -0.1700
Data Index: 8753653 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.6670. Min Act: -0.1700
Data Index: 2690540 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.6045. Min Act: -0.1700
Data Index: 109818 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.6357. Min Act: -0.1700
Data Index: 8587124 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.6357. Min Act: -0.1700
Data Index: 3308191 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.6357. Min Act: -0.1700
Data Index: 4955711 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.5732. Min Act: -0.1700
Data Index: 4422187 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.5420. Min Act: -0.1700
Data Index: 8355077 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.5732. Min Act: -0.1700
Data Index: 173595 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.4795. Min Act: -0.1700
Data Index: 6924844 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.5107. Min Act: -0.1700
Data Index: 1269937 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.5107. Min Act: -0.1700
Data Index: 4871350 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9170. Min Range: -4.9170
Max Act: 4.4795. Min Act: -0.1700
Data Index: 4044429 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19