Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1028. Min Range: -7.1028
Max Act: 7.1028. Min Act: -0.1700
Data Index: 5806734 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1028. Min Range: -7.1028
Max Act: 7.0716. Min Act: -0.1700
Data Index: 7619316 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1028. Min Range: -7.1028
Max Act: 7.0091. Min Act: -0.1700
Data Index: 6025732 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.4778. Min Act: -0.1700
Data Index: 1306051 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.4778. Min Act: -0.1700
Data Index: 1011323 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.4466. Min Act: -0.1700
Data Index: 1489777 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.3841. Min Act: -0.1700
Data Index: 5023366 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.3528. Min Act: -0.1700
Data Index: 2287566 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2903. Min Act: -0.1700
Data Index: 7870913 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.3216. Min Act: -0.1700
Data Index: 7012067 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2903. Min Act: -0.1700
Data Index: 6541931 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2903. Min Act: -0.1700
Data Index: 2250507 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2591. Min Act: -0.1700
Data Index: 7952657 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2903. Min Act: -0.1700
Data Index: 3012417 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2591. Min Act: -0.1700
Data Index: 1502489 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2278. Min Act: -0.1700
Data Index: 2781017 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2278. Min Act: -0.1700
Data Index: 2849875 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.2278. Min Act: -0.1700
Data Index: 3797879 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.1966. Min Act: -0.1700
Data Index: 2860032 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1028. Min Range: -7.1028
Max Act: 6.1653. Min Act: -0.1700
Data Index: 3455405 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19