Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.4241. Min Act: -0.1700
Data Index: 5625915 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.3616. Min Act: -0.1700
Data Index: 2824351 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.3616. Min Act: -0.1700
Data Index: 5880903 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.3616. Min Act: -0.1700
Data Index: 947730 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.1429. Min Act: -0.1700
Data Index: 1883444 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.1116. Min Act: -0.1700
Data Index: 14081 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.0804. Min Act: -0.1700
Data Index: 316504 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.0491. Min Act: -0.1700
Data Index: 4176746 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.0179. Min Act: -0.1700
Data Index: 4986752 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.0179. Min Act: -0.1700
Data Index: 2030846 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.0491. Min Act: -0.1700
Data Index: 332553 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9866. Min Act: -0.1700
Data Index: 4177998 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4241. Min Range: -5.4241
Max Act: 5.0179. Min Act: -0.1700
Data Index: 2408349 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9866. Min Act: -0.1700
Data Index: 4797752 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9866. Min Act: -0.1700
Data Index: 7539235 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9554. Min Act: -0.1700
Data Index: 7206161 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9866. Min Act: -0.1700
Data Index: 3441993 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9866. Min Act: -0.1700
Data Index: 3376337 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9554. Min Act: -0.1700
Data Index: 1805958 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4241. Min Range: -5.4241
Max Act: 4.9866. Min Act: -0.1700
Data Index: 1480666 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19