Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0883. Min Range: -11.0883
Max Act: 11.0883. Min Act: -0.1700
Data Index: 2614188 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.8383. Min Act: -0.1700
Data Index: 2856824 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.8383. Min Act: -0.1700
Data Index: 3682957 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.7133. Min Act: -0.1700
Data Index: 3912283 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5883. Min Act: -0.1700
Data Index: 3223285 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5883. Min Act: -0.1700
Data Index: 2003103 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5258. Min Act: -0.1700
Data Index: 8440386 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5258. Min Act: -0.1700
Data Index: 4432198 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5258. Min Act: -0.1700
Data Index: 1361542 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5258. Min Act: -0.1700
Data Index: 6499651 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 1121099 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.5258. Min Act: -0.1700
Data Index: 7244064 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 6782468 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4633. Min Act: -0.1700
Data Index: 8770561 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4633. Min Act: -0.1700
Data Index: 1328082 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 7046919 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 4018766 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 1620334 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 7311099 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0883. Min Range: -11.0883
Max Act: 10.4008. Min Act: -0.1700
Data Index: 7593122 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19