Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.3259. Min Act: -0.1700
Data Index: 8459186 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.2322. Min Act: -0.1700
Data Index: 7508916 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.1697. Min Act: -0.1700
Data Index: 745883 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.1072. Min Act: -0.1700
Data Index: 8646958 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.1072. Min Act: -0.1700
Data Index: 4972314 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.0134. Min Act: -0.1700
Data Index: 7222883 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3259. Min Range: -5.3259
Max Act: 5.0134. Min Act: -0.1700
Data Index: 8272283 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 4894999 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 4215535 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 65124 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 7133288 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 2606030 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 2366330 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1411283 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 4743205 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1554483 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9822. Min Act: -0.1700
Data Index: 778469 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9509. Min Act: -0.1700
Data Index: 5673689 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1537879 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3259. Min Range: -5.3259
Max Act: 4.9197. Min Act: -0.1700
Data Index: 4463125 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19