Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1129 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1127. Min Range: -4.1127
Max Act: 4.1127. Min Act: -0.1700
Data Index: 1381660 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1127. Min Range: -4.1127
Max Act: 4.0501. Min Act: -0.1700
Data Index: 8304193 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1127. Min Range: -4.1127
Max Act: 4.0501. Min Act: -0.1700
Data Index: 3359927 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1127. Min Range: -4.1127
Max Act: 4.0189. Min Act: -0.1700
Data Index: 3014905 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9876. Min Act: -0.1700
Data Index: 1791541 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9251. Min Act: -0.1700
Data Index: 8063081 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9564. Min Act: -0.1700
Data Index: 4437801 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9564. Min Act: -0.1700
Data Index: 3546420 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9251. Min Act: -0.1700
Data Index: 6857948 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9251. Min Act: -0.1700
Data Index: 4246431 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9251. Min Act: -0.1700
Data Index: 1209194 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.9251. Min Act: -0.1700
Data Index: 7073263 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8938. Min Act: -0.1700
Data Index: 1521251 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8938. Min Act: -0.1700
Data Index: 879504 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8626. Min Act: -0.1700
Data Index: 5457579 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8626. Min Act: -0.1700
Data Index: 1781417 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8626. Min Act: -0.1700
Data Index: 4108767 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8938. Min Act: -0.1700
Data Index: 1110688 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8626. Min Act: -0.1700
Data Index: 4261736 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1127. Min Range: -4.1127
Max Act: 3.8626. Min Act: -0.1700
Data Index: 1041684 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19