Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2574 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.2751. Min Act: -0.1700
Data Index: 375351 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.2439. Min Act: -0.1700
Data Index: 8418133 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.1501. Min Act: -0.1700
Data Index: 6974873 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.1501. Min Act: -0.1700
Data Index: 6115382 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.1189. Min Act: -0.1700
Data Index: 1438887 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.1189. Min Act: -0.1700
Data Index: 8674907 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.0876. Min Act: -0.1700
Data Index: 4936429 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.0876. Min Act: -0.1700
Data Index: 5048349 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.0564. Min Act: -0.1700
Data Index: 6524733 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.0251. Min Act: -0.1700
Data Index: 7644060 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9939. Min Act: -0.1700
Data Index: 5532018 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9939. Min Act: -0.1700
Data Index: 5945122 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2751. Min Range: -5.2751
Max Act: 5.0251. Min Act: -0.1700
Data Index: 162428 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9939. Min Act: -0.1700
Data Index: 3772812 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9939. Min Act: -0.1700
Data Index: 6899982 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9626. Min Act: -0.1700
Data Index: 1609696 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9626. Min Act: -0.1700
Data Index: 2599857 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9314. Min Act: -0.1700
Data Index: 2671276 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9314. Min Act: -0.1700
Data Index: 3056886 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2751. Min Range: -5.2751
Max Act: 4.9314. Min Act: -0.1700
Data Index: 4001335 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19