Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4416 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.1836. Min Act: -0.1700
Data Index: 5596508 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.1523. Min Act: -0.1700
Data Index: 5161774 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.1211. Min Act: -0.1700
Data Index: 2191117 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.1211. Min Act: -0.1700
Data Index: 8115341 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.0898. Min Act: -0.1700
Data Index: 3032913 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.0898. Min Act: -0.1700
Data Index: 5874334 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.0586. Min Act: -0.1700
Data Index: 268103 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.0586. Min Act: -0.1700
Data Index: 8313310 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.0273. Min Act: -0.1700
Data Index: 8027671 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1836. Min Range: -5.1836
Max Act: 5.0273. Min Act: -0.1700
Data Index: 6663841 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6801936 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9961. Min Act: -0.1700
Data Index: 1029411 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9648. Min Act: -0.1700
Data Index: 514615 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6643939 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9961. Min Act: -0.1700
Data Index: 3868540 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9648. Min Act: -0.1700
Data Index: 7782431 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9648. Min Act: -0.1700
Data Index: 932345 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9336. Min Act: -0.1700
Data Index: 3628381 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9648. Min Act: -0.1700
Data Index: 7600890 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1836. Min Range: -5.1836
Max Act: 4.9336. Min Act: -0.1700
Data Index: 5249236 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19