Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5996 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.3132. Min Act: -0.1700
Data Index: 2149325 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.2507. Min Act: -0.1700
Data Index: 5492168 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.1570. Min Act: -0.1700
Data Index: 7874360 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.1570. Min Act: -0.1700
Data Index: 4558468 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.1257. Min Act: -0.1700
Data Index: 3657279 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.0945. Min Act: -0.1700
Data Index: 6452620 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.0632. Min Act: -0.1700
Data Index: 1718085 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.0319. Min Act: -0.1700
Data Index: 3339962 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.0319. Min Act: -0.1700
Data Index: 2102641 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.0007. Min Act: -0.1700
Data Index: 5060572 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3132. Min Range: -4.3132
Max Act: 4.0007. Min Act: -0.1700
Data Index: 4173091 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9694. Min Act: -0.1700
Data Index: 112251 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9694. Min Act: -0.1700
Data Index: 602889 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9694. Min Act: -0.1700
Data Index: 3520250 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9382. Min Act: -0.1700
Data Index: 1578321 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9382. Min Act: -0.1700
Data Index: 2534648 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9382. Min Act: -0.1700
Data Index: 5772293 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9069. Min Act: -0.1700
Data Index: 4522440 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9069. Min Act: -0.1700
Data Index: 5075838 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3132. Min Range: -4.3132
Max Act: 3.9069. Min Act: -0.1700
Data Index: 5143396 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19