Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 126 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1452. Min Range: -8.1452
Max Act: 8.1452. Min Act: -0.1700
Data Index: 7316783 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1452. Min Range: -8.1452
Max Act: 8.0827. Min Act: -0.1700
Data Index: 5501588 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.9577. Min Act: -0.1700
Data Index: 666315 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.8952. Min Act: -0.1700
Data Index: 1293276 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.8952. Min Act: -0.1700
Data Index: 5378117 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.7702. Min Act: -0.1700
Data Index: 8206840 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.7702. Min Act: -0.1700
Data Index: 3185910 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.7077. Min Act: -0.1700
Data Index: 3028878 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.6452. Min Act: -0.1700
Data Index: 6297161 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.7077. Min Act: -0.1700
Data Index: 7621531 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.7077. Min Act: -0.1700
Data Index: 7010946 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.7077. Min Act: -0.1700
Data Index: 3972837 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.6452. Min Act: -0.1700
Data Index: 165970 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.6452. Min Act: -0.1700
Data Index: 4937499 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.5827. Min Act: -0.1700
Data Index: 3387883 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.5827. Min Act: -0.1700
Data Index: 4807903 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.5827. Min Act: -0.1700
Data Index: 1738366 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.5827. Min Act: -0.1700
Data Index: 1916141 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.5827. Min Act: -0.1700
Data Index: 5429765 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1452. Min Range: -8.1452
Max Act: 7.5827. Min Act: -0.1700
Data Index: 2583389 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19