Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1180. Min Range: -6.1180
Max Act: 6.1180. Min Act: -0.1700
Data Index: 3402684 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.9930. Min Act: -0.1700
Data Index: 7058196 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1180. Min Range: -6.1180
Max Act: 6.0243. Min Act: -0.1700
Data Index: 1131397 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.9618. Min Act: -0.1700
Data Index: 8392108 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.9618. Min Act: -0.1700
Data Index: 7784703 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.9305. Min Act: -0.1700
Data Index: 5466385 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.9305. Min Act: -0.1700
Data Index: 6178842 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8680. Min Act: -0.1700
Data Index: 3909850 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8993. Min Act: -0.1700
Data Index: 506609 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8993. Min Act: -0.1700
Data Index: 2242931 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8680. Min Act: -0.1700
Data Index: 551163 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8368. Min Act: -0.1700
Data Index: 1103142 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8680. Min Act: -0.1700
Data Index: 7370739 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8680. Min Act: -0.1700
Data Index: 4588117 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8680. Min Act: -0.1700
Data Index: 354436 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8680. Min Act: -0.1700
Data Index: 2581673 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8368. Min Act: -0.1700
Data Index: 3589208 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8368. Min Act: -0.1700
Data Index: 6534494 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8368. Min Act: -0.1700
Data Index: 5652316 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1180. Min Range: -6.1180
Max Act: 5.8055. Min Act: -0.1700
Data Index: 4925961 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19