Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5387 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.4867. Min Act: -0.1700
Data Index: 1348721 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.4555. Min Act: -0.1700
Data Index: 4395447 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1257432 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.3617. Min Act: -0.1700
Data Index: 5388115 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2992. Min Act: -0.1700
Data Index: 1054352 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2680. Min Act: -0.1700
Data Index: 6157572 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2992. Min Act: -0.1700
Data Index: 578905 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.3305. Min Act: -0.1700
Data Index: 7617737 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2992. Min Act: -0.1700
Data Index: 2671765 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2680. Min Act: -0.1700
Data Index: 4870818 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2680. Min Act: -0.1700
Data Index: 6701430 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2367. Min Act: -0.1700
Data Index: 6266108 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2367. Min Act: -0.1700
Data Index: 147121 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2367. Min Act: -0.1700
Data Index: 66073 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2055. Min Act: -0.1700
Data Index: 4129670 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2367. Min Act: -0.1700
Data Index: 5629453 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2055. Min Act: -0.1700
Data Index: 3218906 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2055. Min Act: -0.1700
Data Index: 3079411 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.2055. Min Act: -0.1700
Data Index: 1962788 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4867. Min Range: -5.4867
Max Act: 5.1742. Min Act: -0.1700
Data Index: 7109268 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19