Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1031. Min Range: -7.1031
Max Act: 7.1031. Min Act: -0.1700
Data Index: 3393041 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1031. Min Range: -7.1031
Max Act: 7.0093. Min Act: -0.1700
Data Index: 4369642 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.9156. Min Act: -0.1700
Data Index: 4901473 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.8843. Min Act: -0.1700
Data Index: 6199856 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.8843. Min Act: -0.1700
Data Index: 8135807 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.8218. Min Act: -0.1700
Data Index: 4915091 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.8218. Min Act: -0.1700
Data Index: 4853052 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7593. Min Act: -0.1700
Data Index: 5616384 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7593. Min Act: -0.1700
Data Index: 7374019 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7906. Min Act: -0.1700
Data Index: 2734947 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7593. Min Act: -0.1700
Data Index: 75473 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7281. Min Act: -0.1700
Data Index: 7253235 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7281. Min Act: -0.1700
Data Index: 1357619 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.7281. Min Act: -0.1700
Data Index: 2093429 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.6968. Min Act: -0.1700
Data Index: 8131249 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.6968. Min Act: -0.1700
Data Index: 7751503 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.6343. Min Act: -0.1700
Data Index: 1327142 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.6343. Min Act: -0.1700
Data Index: 4451510 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.6343. Min Act: -0.1700
Data Index: 6955562 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1031. Min Range: -7.1031
Max Act: 6.5718. Min Act: -0.1700
Data Index: 7517040 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19