Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5287 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.2764. Min Act: -0.1700
Data Index: 2113613 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.1827. Min Act: -0.1700
Data Index: 4060905 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0889. Min Act: -0.1700
Data Index: 2712844 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0264. Min Act: -0.1700
Data Index: 5290113 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0264. Min Act: -0.1700
Data Index: 6498174 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0264. Min Act: -0.1700
Data Index: 4791938 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2764. Min Range: -5.2764
Max Act: 5.0264. Min Act: -0.1700
Data Index: 8450934 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 2653555 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 5387512 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 5681258 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 7768909 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 2544032 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 3829032 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9952. Min Act: -0.1700
Data Index: 7875626 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 3884131 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9327. Min Act: -0.1700
Data Index: 2229172 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 5111714 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 7091423 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9639. Min Act: -0.1700
Data Index: 5875414 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2764. Min Range: -5.2764
Max Act: 4.9327. Min Act: -0.1700
Data Index: 2237236 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19