Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1519 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2010. Min Range: -10.2010
Max Act: 10.2010. Min Act: -0.1700
Data Index: 1405900 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2010. Min Range: -10.2010
Max Act: 10.0135. Min Act: -0.1700
Data Index: 2180111 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.8260. Min Act: -0.1700
Data Index: 2343749 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.7010. Min Act: -0.1700
Data Index: 396421 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.5760. Min Act: -0.1700
Data Index: 7561293 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.3260. Min Act: -0.1700
Data Index: 1539467 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.3260. Min Act: -0.1700
Data Index: 5082432 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.3260. Min Act: -0.1700
Data Index: 4587538 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.3260. Min Act: -0.1700
Data Index: 1610375 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.3260. Min Act: -0.1700
Data Index: 3798603 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2635. Min Act: -0.1700
Data Index: 7933632 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2635. Min Act: -0.1700
Data Index: 8394815 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2010. Min Act: -0.1700
Data Index: 226819 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2010. Min Act: -0.1700
Data Index: 2486891 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2010. Min Act: -0.1700
Data Index: 5051758 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2010. Min Act: -0.1700
Data Index: 1981234 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.2010. Min Act: -0.1700
Data Index: 6310702 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.1385. Min Act: -0.1700
Data Index: 7673649 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.1385. Min Act: -0.1700
Data Index: 906446 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2010. Min Range: -10.2010
Max Act: 9.1385. Min Act: -0.1700
Data Index: 5461956 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19