Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5482 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.7452. Min Act: -0.1700
Data Index: 1924846 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.6827. Min Act: -0.1700
Data Index: 7199234 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5889. Min Act: -0.1700
Data Index: 5031964 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.6202. Min Act: -0.1700
Data Index: 1660338 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5889. Min Act: -0.1700
Data Index: 4862034 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5889. Min Act: -0.1700
Data Index: 279520 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5889. Min Act: -0.1700
Data Index: 1846148 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5889. Min Act: -0.1700
Data Index: 5733407 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7723637 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 4463502 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7701417 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7309234 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 2021271 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7833409 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 2595234 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 5454035 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7462216 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.4952. Min Act: -0.1700
Data Index: 3202938 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.4952. Min Act: -0.1700
Data Index: 2263467 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7452. Min Range: -5.7452
Max Act: 5.5264. Min Act: -0.1700
Data Index: 4736024 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19