Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1156. Min Range: -6.1156
Max Act: 6.1156. Min Act: -0.1700
Data Index: 3917341 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1156. Min Range: -6.1156
Max Act: 6.0844. Min Act: -0.1700
Data Index: 1302651 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8344. Min Act: -0.1700
Data Index: 3770359 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 6567573 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8031. Min Act: -0.1700
Data Index: 7816242 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7719. Min Act: -0.1700
Data Index: 3293021 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8031. Min Act: -0.1700
Data Index: 3323669 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8031. Min Act: -0.1700
Data Index: 4775047 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 501784 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 6217141 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 6033149 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 3982436 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 1127516 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 3469806 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 776316 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 1047238 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 272918 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7406. Min Act: -0.1700
Data Index: 4664896 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.7094. Min Act: -0.1700
Data Index: 5966776 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.6781. Min Act: -0.1700
Data Index: 55018 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19