Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1421 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3063. Min Range: -6.3063
Max Act: 6.3063. Min Act: -0.1700
Data Index: 1403097 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3063. Min Range: -6.3063
Max Act: 6.0563. Min Act: -0.1700
Data Index: 1159055 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3063. Min Range: -6.3063
Max Act: 6.0250. Min Act: -0.1700
Data Index: 3636134 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.9625. Min Act: -0.1700
Data Index: 1432833 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.9000. Min Act: -0.1700
Data Index: 5866541 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8688. Min Act: -0.1700
Data Index: 6810220 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.9000. Min Act: -0.1700
Data Index: 1151673 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8688. Min Act: -0.1700
Data Index: 4059802 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8688. Min Act: -0.1700
Data Index: 7894496 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8375. Min Act: -0.1700
Data Index: 1281251 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8375. Min Act: -0.1700
Data Index: 522542 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8063. Min Act: -0.1700
Data Index: 6513394 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8063. Min Act: -0.1700
Data Index: 7668146 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.8063. Min Act: -0.1700
Data Index: 2427041 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.7750. Min Act: -0.1700
Data Index: 1281253 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.7750. Min Act: -0.1700
Data Index: 62556 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.7750. Min Act: -0.1700
Data Index: 4281021 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.7438. Min Act: -0.1700
Data Index: 6173260 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.7438. Min Act: -0.1700
Data Index: 1403098 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3063. Min Range: -6.3063
Max Act: 5.7125. Min Act: -0.1700
Data Index: 7503432 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19