Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4843 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.6694. Min Act: -0.1700
Data Index: 6451099 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.3256. Min Act: -0.1700
Data Index: 4278850 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2944. Min Act: -0.1700
Data Index: 3482603 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4321267 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2631. Min Act: -0.1700
Data Index: 6991143 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2631. Min Act: -0.1700
Data Index: 3179966 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2319. Min Act: -0.1700
Data Index: 4438113 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2631. Min Act: -0.1700
Data Index: 4151806 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2006. Min Act: -0.1700
Data Index: 7455802 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2319. Min Act: -0.1700
Data Index: 7405543 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2006. Min Act: -0.1700
Data Index: 301643 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 5124038 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1381. Min Act: -0.1700
Data Index: 110999 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 4017511 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 6231804 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 5206588 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 4504859 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 1636385 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 6390596 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 587737 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19