Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4548 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.3746. Min Act: -0.1700
Data Index: 5167008 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.2496. Min Act: -0.1700
Data Index: 1469476 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3746. Min Range: -5.3746
Max Act: 5.1871. Min Act: -0.1700
Data Index: 2041613 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9371. Min Act: -0.1700
Data Index: 2004968 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9684. Min Act: -0.1700
Data Index: 2827516 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9684. Min Act: -0.1700
Data Index: 6126860 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9371. Min Act: -0.1700
Data Index: 5995544 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9059. Min Act: -0.1700
Data Index: 4269191 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.9059. Min Act: -0.1700
Data Index: 2827517 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.8434. Min Act: -0.1700
Data Index: 7731418 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.7184. Min Act: -0.1700
Data Index: 7525837 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.7184. Min Act: -0.1700
Data Index: 4698173 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6871. Min Act: -0.1700
Data Index: 4143439 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6871. Min Act: -0.1700
Data Index: 1280370 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6871. Min Act: -0.1700
Data Index: 2566161 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6871. Min Act: -0.1700
Data Index: 7333145 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6871. Min Act: -0.1700
Data Index: 3712539 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6559. Min Act: -0.1700
Data Index: 5285233 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6559. Min Act: -0.1700
Data Index: 5701278 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3746. Min Range: -5.3746
Max Act: 4.6246. Min Act: -0.1700
Data Index: 5961723 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19