Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.2951. Min Act: -0.1700
Data Index: 389328 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.2639. Min Act: -0.1700
Data Index: 4123701 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.2326. Min Act: -0.1700
Data Index: 4728762 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.1701. Min Act: -0.1700
Data Index: 5295374 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.1389. Min Act: -0.1700
Data Index: 6369940 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.1076. Min Act: -0.1700
Data Index: 223434 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.1076. Min Act: -0.1700
Data Index: 153442 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 2540999 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 2298526 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.1076. Min Act: -0.1700
Data Index: 8063918 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 5456620 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 1535361 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 6272060 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 234688 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0764. Min Act: -0.1700
Data Index: 6496894 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0451. Min Act: -0.1700
Data Index: 6006969 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0451. Min Act: -0.1700
Data Index: 2345753 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0451. Min Act: -0.1700
Data Index: 980884 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0451. Min Act: -0.1700
Data Index: 100688 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2951. Min Range: -5.2951
Max Act: 5.0139. Min Act: -0.1700
Data Index: 8482749 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19