Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0092. Min Range: -6.0092
Max Act: 6.0092. Min Act: -0.1700
Data Index: 4737294 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.7279. Min Act: -0.1700
Data Index: 1928807 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.6654. Min Act: -0.1700
Data Index: 8477151 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.6342. Min Act: -0.1700
Data Index: 5170211 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.6029. Min Act: -0.1700
Data Index: 5847406 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.6029. Min Act: -0.1700
Data Index: 648252 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5717. Min Act: -0.1700
Data Index: 5903579 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5404. Min Act: -0.1700
Data Index: 4507468 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5404. Min Act: -0.1700
Data Index: 6069416 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5404. Min Act: -0.1700
Data Index: 5170210 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5092. Min Act: -0.1700
Data Index: 6167694 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5092. Min Act: -0.1700
Data Index: 4179955 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5092. Min Act: -0.1700
Data Index: 1937905 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.4779. Min Act: -0.1700
Data Index: 6874908 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.5092. Min Act: -0.1700
Data Index: 7813617 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.4779. Min Act: -0.1700
Data Index: 4572022 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.4779. Min Act: -0.1700
Data Index: 3602503 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.4467. Min Act: -0.1700
Data Index: 4685727 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.4467. Min Act: -0.1700
Data Index: 2217389 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0092. Min Range: -6.0092
Max Act: 5.4467. Min Act: -0.1700
Data Index: 5008599 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19