Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5570 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.1188. Min Act: -0.1700
Data Index: 5112316 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 634297 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 1073238 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 8680459 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0876. Min Act: -0.1700
Data Index: 8666653 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0563. Min Act: -0.1700
Data Index: 7906104 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0563. Min Act: -0.1700
Data Index: 8113259 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0251. Min Act: -0.1700
Data Index: 7906103 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0251. Min Act: -0.1700
Data Index: 7762961 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0251. Min Act: -0.1700
Data Index: 4363932 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0251. Min Act: -0.1700
Data Index: 7512800 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9938. Min Act: -0.1700
Data Index: 5888131 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1188. Min Range: -6.1188
Max Act: 6.0251. Min Act: -0.1700
Data Index: 1090712 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9938. Min Act: -0.1700
Data Index: 6594314 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9938. Min Act: -0.1700
Data Index: 6163447 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9938. Min Act: -0.1700
Data Index: 2084588 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9938. Min Act: -0.1700
Data Index: 542603 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9626. Min Act: -0.1700
Data Index: 3306842 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9626. Min Act: -0.1700
Data Index: 1975772 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1188. Min Range: -6.1188
Max Act: 5.9938. Min Act: -0.1700
Data Index: 2051789 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19