Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.7930. Min Act: -0.1700
Data Index: 2539712 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.7930. Min Act: -0.1700
Data Index: 4365893 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.7617. Min Act: -0.1700
Data Index: 3992384 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.7617. Min Act: -0.1700
Data Index: 3670195 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.7617. Min Act: -0.1700
Data Index: 1552798 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.7617. Min Act: -0.1700
Data Index: 3716503 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6992. Min Act: -0.1700
Data Index: 8594187 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6992. Min Act: -0.1700
Data Index: 2906447 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6367. Min Act: -0.1700
Data Index: 2622895 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6680. Min Act: -0.1700
Data Index: 3448736 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6680. Min Act: -0.1700
Data Index: 7770416 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6680. Min Act: -0.1700
Data Index: 4885200 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6367. Min Act: -0.1700
Data Index: 6069123 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6055. Min Act: -0.1700
Data Index: 1433517 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6055. Min Act: -0.1700
Data Index: 4236753 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.6055. Min Act: -0.1700
Data Index: 278997 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.5742. Min Act: -0.1700
Data Index: 8630972 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.5742. Min Act: -0.1700
Data Index: 2107657 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.5430. Min Act: -0.1700
Data Index: 7856113 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7930. Min Range: -6.7930
Max Act: 6.5430. Min Act: -0.1700
Data Index: 3019468 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19