Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 504 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0711. Min Range: -5.0711
Max Act: 5.0711. Min Act: -0.1700
Data Index: 528812 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0711. Min Range: -5.0711
Max Act: 5.0086. Min Act: -0.1700
Data Index: 8319676 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.9149. Min Act: -0.1700
Data Index: 6062755 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.8524. Min Act: -0.1700
Data Index: 443595 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.8836. Min Act: -0.1700
Data Index: 6062756 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.8524. Min Act: -0.1700
Data Index: 7873142 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.8524. Min Act: -0.1700
Data Index: 6062757 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7899. Min Act: -0.1700
Data Index: 3568893 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7899. Min Act: -0.1700
Data Index: 5302314 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7586. Min Act: -0.1700
Data Index: 2353695 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7586. Min Act: -0.1700
Data Index: 2593437 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7586. Min Act: -0.1700
Data Index: 4818569 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7586. Min Act: -0.1700
Data Index: 7547728 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7586. Min Act: -0.1700
Data Index: 7292202 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.6961. Min Act: -0.1700
Data Index: 7120851 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7274. Min Act: -0.1700
Data Index: 3179144 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1692209 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1293324 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.7274. Min Act: -0.1700
Data Index: 1745564 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0711. Min Range: -5.0711
Max Act: 4.6961. Min Act: -0.1700
Data Index: 7003810 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19