Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1890. Min Range: -4.1890
Max Act: 4.1890. Min Act: -0.1700
Data Index: 5799356 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.9077. Min Act: -0.1700
Data Index: 8325667 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8452. Min Act: -0.1700
Data Index: 1137239 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8452. Min Act: -0.1700
Data Index: 1039803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8452. Min Act: -0.1700
Data Index: 8567023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8452. Min Act: -0.1700
Data Index: 689617 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8452. Min Act: -0.1700
Data Index: 3943125 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8139. Min Act: -0.1700
Data Index: 876751 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.8139. Min Act: -0.1700
Data Index: 1303713 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7826. Min Act: -0.1700
Data Index: 7277016 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7826. Min Act: -0.1700
Data Index: 1618656 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7826. Min Act: -0.1700
Data Index: 1299176 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7826. Min Act: -0.1700
Data Index: 3756724 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7826. Min Act: -0.1700
Data Index: 1338150 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7513. Min Act: -0.1700
Data Index: 6667186 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7513. Min Act: -0.1700
Data Index: 5475682 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7513. Min Act: -0.1700
Data Index: 2776958 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7201. Min Act: -0.1700
Data Index: 118140 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7201. Min Act: -0.1700
Data Index: 3027280 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1890. Min Range: -4.1890
Max Act: 3.7201. Min Act: -0.1700
Data Index: 6162714 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19