Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 899 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.8622. Min Act: -0.1700
Data Index: 3508575 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.7060. Min Act: -0.1700
Data Index: 2978216 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.7060. Min Act: -0.1700
Data Index: 7244567 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.6435. Min Act: -0.1700
Data Index: 5894720 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2955468 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.5810. Min Act: -0.1700
Data Index: 1578453 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.5497. Min Act: -0.1700
Data Index: 582854 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.5185. Min Act: -0.1700
Data Index: 7072482 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.5497. Min Act: -0.1700
Data Index: 3381028 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4872. Min Act: -0.1700
Data Index: 3201354 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4560. Min Act: -0.1700
Data Index: 2747134 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 153119 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 2279997 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 7472406 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 343718 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 4983535 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 6181807 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.3935. Min Act: -0.1700
Data Index: 3061373 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.4247. Min Act: -0.1700
Data Index: 6154208 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8622. Min Range: -5.8622
Max Act: 5.3935. Min Act: -0.1700
Data Index: 7399048 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19