Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.9150. Min Act: -0.1700
Data Index: 221009 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.5713. Min Act: -0.1700
Data Index: 3960595 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.6025. Min Act: -0.1700
Data Index: 4702989 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.5713. Min Act: -0.1700
Data Index: 1418694 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.5713. Min Act: -0.1700
Data Index: 7280047 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.5400. Min Act: -0.1700
Data Index: 3950858 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.5088. Min Act: -0.1700
Data Index: 5427705 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.4150. Min Act: -0.1700
Data Index: 2391324 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.4463. Min Act: -0.1700
Data Index: 501710 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.4463. Min Act: -0.1700
Data Index: 11132 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.4150. Min Act: -0.1700
Data Index: 7288030 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.3838. Min Act: -0.1700
Data Index: 5551999 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.4150. Min Act: -0.1700
Data Index: 3074740 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.3838. Min Act: -0.1700
Data Index: 4758246 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.4150. Min Act: -0.1700
Data Index: 4854951 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.3838. Min Act: -0.1700
Data Index: 4228497 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.3525. Min Act: -0.1700
Data Index: 5502606 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.3525. Min Act: -0.1700
Data Index: 3759025 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.3213. Min Act: -0.1700
Data Index: 5290373 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9150. Min Range: -7.9150
Max Act: 7.2900. Min Act: -0.1700
Data Index: 6161807 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19