Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5120. Min Range: -6.5120
Max Act: 6.5120. Min Act: -0.1700
Data Index: 5394411 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5120. Min Range: -6.5120
Max Act: 6.1682. Min Act: -0.1700
Data Index: 5865668 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5120. Min Range: -6.5120
Max Act: 6.1057. Min Act: -0.1700
Data Index: 4944982 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5120. Min Range: -6.5120
Max Act: 6.0745. Min Act: -0.1700
Data Index: 273708 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.9807. Min Act: -0.1700
Data Index: 1080191 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.9182. Min Act: -0.1700
Data Index: 3622172 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.8557. Min Act: -0.1700
Data Index: 3055828 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.8557. Min Act: -0.1700
Data Index: 5048224 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.8245. Min Act: -0.1700
Data Index: 5738827 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7307. Min Act: -0.1700
Data Index: 3852202 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7620. Min Act: -0.1700
Data Index: 2777918 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7620. Min Act: -0.1700
Data Index: 2777919 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7620. Min Act: -0.1700
Data Index: 5192355 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7620. Min Act: -0.1700
Data Index: 7687236 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7620. Min Act: -0.1700
Data Index: 5017540 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7307. Min Act: -0.1700
Data Index: 7817214 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7307. Min Act: -0.1700
Data Index: 3527805 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7307. Min Act: -0.1700
Data Index: 7067301 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7307. Min Act: -0.1700
Data Index: 1682097 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5120. Min Range: -6.5120
Max Act: 5.7307. Min Act: -0.1700
Data Index: 5114163 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19