Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.7261. Min Act: -0.1700
Data Index: 5628843 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.5386. Min Act: -0.1700
Data Index: 1571488 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.4136. Min Act: -0.1700
Data Index: 8346702 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.3824. Min Act: -0.1700
Data Index: 4879803 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1636. Min Act: -0.1700
Data Index: 8784204 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1636. Min Act: -0.1700
Data Index: 8560029 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1324. Min Act: -0.1700
Data Index: 7627151 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1324. Min Act: -0.1700
Data Index: 1850860 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1011. Min Act: -0.1700
Data Index: 1638850 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1324. Min Act: -0.1700
Data Index: 5652275 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1011. Min Act: -0.1700
Data Index: 188600 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 3065489 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0699. Min Act: -0.1700
Data Index: 188606 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0699. Min Act: -0.1700
Data Index: 1553503 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0699. Min Act: -0.1700
Data Index: 3532839 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0699. Min Act: -0.1700
Data Index: 188599 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6335850 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 1638820 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6177952 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5554223 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19