Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.6724. Min Act: -0.1700
Data Index: 7887398 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.2661. Min Act: -0.1700
Data Index: 477703 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.1724. Min Act: -0.1700
Data Index: 7453129 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.1724. Min Act: -0.1700
Data Index: 6199961 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.1724. Min Act: -0.1700
Data Index: 821081 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.1099. Min Act: -0.1700
Data Index: 8531691 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 1999954 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 6447846 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0161. Min Act: -0.1700
Data Index: 4106421 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0161. Min Act: -0.1700
Data Index: 6820088 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 948884 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0161. Min Act: -0.1700
Data Index: 5196650 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0161. Min Act: -0.1700
Data Index: 3508927 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6724. Min Range: -6.6724
Max Act: 6.0161. Min Act: -0.1700
Data Index: 562003 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6724. Min Range: -6.6724
Max Act: 5.9536. Min Act: -0.1700
Data Index: 3194996 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6724. Min Range: -6.6724
Max Act: 5.9224. Min Act: -0.1700
Data Index: 2491107 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6724. Min Range: -6.6724
Max Act: 5.8911. Min Act: -0.1700
Data Index: 3246069 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6724. Min Range: -6.6724
Max Act: 5.8911. Min Act: -0.1700
Data Index: 3422747 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6724. Min Range: -6.6724
Max Act: 5.8911. Min Act: -0.1700
Data Index: 5196170 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6724. Min Range: -6.6724
Max Act: 5.8911. Min Act: -0.1700
Data Index: 7258672 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19