Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.3408. Min Act: -0.1700
Data Index: 6369718 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3408. Min Range: -7.3408
Max Act: 7.2158. Min Act: -0.1700
Data Index: 8321973 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9970. Min Act: -0.1700
Data Index: 2594810 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9345. Min Act: -0.1700
Data Index: 1606697 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9345. Min Act: -0.1700
Data Index: 8475503 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9033. Min Act: -0.1700
Data Index: 5644489 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.9345. Min Act: -0.1700
Data Index: 6953818 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8720. Min Act: -0.1700
Data Index: 236152 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7783. Min Act: -0.1699
Data Index: 4620306 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.8095. Min Act: -0.1700
Data Index: 6896712 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7783. Min Act: -0.1700
Data Index: 2675722 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7470. Min Act: -0.1700
Data Index: 814881 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7470. Min Act: -0.1700
Data Index: 6056727 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7158. Min Act: -0.1700
Data Index: 3660114 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.7158. Min Act: -0.1700
Data Index: 8802394 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.6845. Min Act: -0.1700
Data Index: 3668211 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.6845. Min Act: -0.1700
Data Index: 8363093 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.6845. Min Act: -0.1700
Data Index: 7281053 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.6845. Min Act: -0.1700
Data Index: 5090043 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3408. Min Range: -7.3408
Max Act: 6.6845. Min Act: -0.1700
Data Index: 1692261 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19