Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0095. Min Range: -8.0095
Max Act: 8.0095. Min Act: -0.1700
Data Index: 6752513 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0095. Min Range: -8.0095
Max Act: 8.0095. Min Act: -0.1700
Data Index: 2174325 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.9470. Min Act: -0.1700
Data Index: 7976993 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.8220. Min Act: -0.1700
Data Index: 3144768 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.7908. Min Act: -0.1700
Data Index: 5445563 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.7595. Min Act: -0.1700
Data Index: 7796610 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.7595. Min Act: -0.1700
Data Index: 5813063 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.7595. Min Act: -0.1700
Data Index: 927147 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6970. Min Act: -0.1700
Data Index: 8677201 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6658. Min Act: -0.1700
Data Index: 6906676 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6658. Min Act: -0.1700
Data Index: 5813064 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6345. Min Act: -0.1700
Data Index: 2174312 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6345. Min Act: -0.1700
Data Index: 2119317 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6033. Min Act: -0.1700
Data Index: 3520943 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.6033. Min Act: -0.1700
Data Index: 1556593 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.5720. Min Act: -0.1700
Data Index: 5384856 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.5720. Min Act: -0.1700
Data Index: 8677200 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.5720. Min Act: -0.1700
Data Index: 5760676 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.5408. Min Act: -0.1700
Data Index: 8450691 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0095. Min Range: -8.0095
Max Act: 7.5408. Min Act: -0.1700
Data Index: 7617842 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19