Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6142 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.6886. Min Act: -0.1700
Data Index: 8475892 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.6574. Min Act: -0.1700
Data Index: 3800113 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.5949. Min Act: -0.1700
Data Index: 2524626 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.5011. Min Act: -0.1700
Data Index: 55160 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.4386. Min Act: -0.1700
Data Index: 7770186 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.4699. Min Act: -0.1700
Data Index: 1700309 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.4386. Min Act: -0.1700
Data Index: 3386482 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2153177 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.4386. Min Act: -0.1700
Data Index: 2284260 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.3761. Min Act: -0.1700
Data Index: 969070 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.3449. Min Act: -0.1700
Data Index: 1700306 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.3136. Min Act: -0.1700
Data Index: 4544778 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2824. Min Act: -0.1700
Data Index: 110619 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2511. Min Act: -0.1700
Data Index: 2220677 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2511. Min Act: -0.1700
Data Index: 7900841 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2738523 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2534106 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2199. Min Act: -0.1700
Data Index: 5991866 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.2199. Min Act: -0.1700
Data Index: 8795668 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6886. Min Range: -5.6886
Max Act: 5.1886. Min Act: -0.1700
Data Index: 306168 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19