Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.7095. Min Act: -0.1698
Data Index: 4797598 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.7095. Min Act: -0.1287
Data Index: 2698211 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.5532. Min Act: -0.1700
Data Index: 2698213 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.4907. Min Act: -0.1700
Data Index: 4797600 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.4907. Min Act: -0.1602
Data Index: 4797599 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.4282. Min Act: -0.1621
Data Index: 2698210 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.3657. Min Act: -0.1579
Data Index: 2698212 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.3657. Min Act: -0.1700
Data Index: 8551124 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.2720. Min Act: -0.1700
Data Index: 905313 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.2720. Min Act: -0.1700
Data Index: 1488526 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.2407. Min Act: -0.1700
Data Index: 563412 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1782. Min Act: -0.1700
Data Index: 8551128 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1782. Min Act: -0.1700
Data Index: 7997965 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8551132 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1470. Min Act: -0.1700
Data Index: 7598807 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8551130 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1470. Min Act: -0.1700
Data Index: 8551122 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1157. Min Act: -0.1700
Data Index: 8551125 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1157. Min Act: -0.1700
Data Index: 8551127 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7095. Min Range: -5.7095
Max Act: 5.1157. Min Act: -0.1700
Data Index: 5022599 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19