Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4363 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.5892. Min Act: -0.1700
Data Index: 5208900 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.4955. Min Act: -0.1700
Data Index: 8357051 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3705. Min Act: -0.1700
Data Index: 6288482 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3705. Min Act: -0.1700
Data Index: 3455004 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3392. Min Act: -0.1700
Data Index: 5563708 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3392. Min Act: -0.1700
Data Index: 754248 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3392. Min Act: -0.1700
Data Index: 2265214 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3392. Min Act: -0.1700
Data Index: 773612 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3392. Min Act: -0.1700
Data Index: 1243850 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3080. Min Act: -0.1700
Data Index: 6789606 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2767. Min Act: -0.1700
Data Index: 1933863 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2767. Min Act: -0.1700
Data Index: 1720704 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.3080. Min Act: -0.1700
Data Index: 1892240 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2767. Min Act: -0.1700
Data Index: 8688266 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2767. Min Act: -0.1700
Data Index: 2912686 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2455. Min Act: -0.1700
Data Index: 814108 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2142. Min Act: -0.1700
Data Index: 3928629 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2142. Min Act: -0.1700
Data Index: 2592367 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2142. Min Act: -0.1700
Data Index: 7904213 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5892. Min Range: -5.5892
Max Act: 5.2142. Min Act: -0.1700
Data Index: 6306915 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19