Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4885 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.5724. Min Act: -0.1700
Data Index: 1471922 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.2911. Min Act: -0.1700
Data Index: 4933524 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1036. Min Act: -0.1700
Data Index: 5789880 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1349. Min Act: -0.1700
Data Index: 8382266 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1661. Min Act: -0.1700
Data Index: 148558 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1349. Min Act: -0.1700
Data Index: 951806 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.1036. Min Act: -0.1700
Data Index: 1471924 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0411. Min Act: -0.1700
Data Index: 1199009 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0724. Min Act: -0.1700
Data Index: 6400831 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0411. Min Act: -0.1700
Data Index: 237988 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0411. Min Act: -0.1700
Data Index: 158888 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0099. Min Act: -0.1700
Data Index: 7943959 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0099. Min Act: -0.1700
Data Index: 2010146 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3203641 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5724. Min Range: -5.5724
Max Act: 4.9786. Min Act: -0.1700
Data Index: 6739313 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5724. Min Range: -5.5724
Max Act: 5.0099. Min Act: -0.1700
Data Index: 6400827 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5724. Min Range: -5.5724
Max Act: 4.9786. Min Act: -0.1700
Data Index: 2503080 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5724. Min Range: -5.5724
Max Act: 4.9786. Min Act: -0.1700
Data Index: 8497362 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5724. Min Range: -5.5724
Max Act: 4.9786. Min Act: -0.1700
Data Index: 2138582 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5724. Min Range: -5.5724
Max Act: 4.9474. Min Act: -0.1700
Data Index: 3377200 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19