Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1506 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.9047. Min Act: -0.1700
Data Index: 2770241 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8735. Min Act: -0.1700
Data Index: 5465383 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8735. Min Act: -0.1700
Data Index: 4427777 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8422. Min Act: -0.1700
Data Index: 7566935 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8735. Min Act: -0.1700
Data Index: 6543694 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8422. Min Act: -0.1700
Data Index: 434250 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8422. Min Act: -0.1700
Data Index: 4730481 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8110. Min Act: -0.1700
Data Index: 1799077 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.8110. Min Act: -0.1700
Data Index: 2215159 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7797. Min Act: -0.1700
Data Index: 302762 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7797. Min Act: -0.1700
Data Index: 2770242 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7797. Min Act: -0.1700
Data Index: 1242709 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7797. Min Act: -0.1700
Data Index: 5075078 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7485. Min Act: -0.1700
Data Index: 2215161 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7485. Min Act: -0.1700
Data Index: 4763004 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7172. Min Act: -0.1700
Data Index: 345289 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7172. Min Act: -0.1700
Data Index: 2770240 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7172. Min Act: -0.1700
Data Index: 2345665 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.7172. Min Act: -0.1700
Data Index: 2972145 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9047. Min Range: -4.9047
Max Act: 4.6860. Min Act: -0.1700
Data Index: 3691075 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19