Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.6205. Min Act: -0.1700
Data Index: 5503683 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.5580. Min Act: -0.1700
Data Index: 1180453 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.5580. Min Act: -0.1700
Data Index: 1644709 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.3080. Min Act: -0.1700
Data Index: 6634337 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.1830. Min Act: -0.1700
Data Index: 857034 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.1830. Min Act: -0.1700
Data Index: 866301 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.0580. Min Act: -0.1700
Data Index: 1225068 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.0580. Min Act: -0.1700
Data Index: 471380 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.9955. Min Act: -0.1700
Data Index: 4446440 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6205. Min Range: -7.6205
Max Act: 7.0267. Min Act: -0.1700
Data Index: 4451399 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.9330. Min Act: -0.1700
Data Index: 4825788 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.9330. Min Act: -0.1700
Data Index: 8049986 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.9017. Min Act: -0.1700
Data Index: 6838499 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.9017. Min Act: -0.1700
Data Index: 3608078 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.9017. Min Act: -0.1700
Data Index: 3374964 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.8392. Min Act: -0.1700
Data Index: 6220451 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.8705. Min Act: -0.1700
Data Index: 7969936 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.7767. Min Act: -0.1700
Data Index: 5522082 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.7767. Min Act: -0.1700
Data Index: 8148847 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6205. Min Range: -7.6205
Max Act: 6.7455. Min Act: -0.1700
Data Index: 2890964 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19