Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.8007. Min Act: -0.1700
Data Index: 8618677 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.7694. Min Act: -0.1700
Data Index: 4344012 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.7694. Min Act: -0.1700
Data Index: 1663868 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.7069. Min Act: -0.1700
Data Index: 3534517 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.6444. Min Act: -0.1700
Data Index: 58350 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.6444. Min Act: -0.1700
Data Index: 7492317 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.6132. Min Act: -0.1700
Data Index: 2337595 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.5819. Min Act: -0.1700
Data Index: 1150970 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.5507. Min Act: -0.1700
Data Index: 1486625 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4882. Min Act: -0.1700
Data Index: 2541684 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4882. Min Act: -0.1700
Data Index: 1276308 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4569. Min Act: -0.1700
Data Index: 540821 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4569. Min Act: -0.1700
Data Index: 929380 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4569. Min Act: -0.1700
Data Index: 3926692 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4569. Min Act: -0.1700
Data Index: 8418041 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4569. Min Act: -0.1700
Data Index: 8148576 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4257. Min Act: -0.1700
Data Index: 3893701 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4257. Min Act: -0.1700
Data Index: 2179763 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.3944. Min Act: -0.1700
Data Index: 7696762 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8007. Min Range: -5.8007
Max Act: 5.4257. Min Act: -0.1700
Data Index: 2876163 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19