Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.6728. Min Act: -0.1700
Data Index: 8062920 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.3916. Min Act: -0.1700
Data Index: 2168939 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.3603. Min Act: -0.1700
Data Index: 5080128 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.2978. Min Act: -0.1700
Data Index: 8034472 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.2666. Min Act: -0.1700
Data Index: 6441741 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.2041. Min Act: -0.1700
Data Index: 2799093 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3530941 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.2041. Min Act: -0.1700
Data Index: 6319434 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.2041. Min Act: -0.1700
Data Index: 1310219 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 1391333 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3717533 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1416. Min Act: -0.1700
Data Index: 7193664 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1416. Min Act: -0.1700
Data Index: 5547075 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1416. Min Act: -0.1700
Data Index: 7123202 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1728. Min Act: -0.1700
Data Index: 6441738 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1416. Min Act: -0.1700
Data Index: 2942925 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1103. Min Act: -0.1700
Data Index: 4148227 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.1103. Min Act: -0.1700
Data Index: 6837526 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.0791. Min Act: -0.1700
Data Index: 6754578 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6728. Min Range: -5.6728
Max Act: 5.0791. Min Act: -0.1700
Data Index: 693038 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19