Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.8684. Min Act: -0.1700
Data Index: 4493164 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.5712. Min Act: -0.1700
Data Index: 7774347 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.5242. Min Act: -0.1700
Data Index: 311316 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.5085. Min Act: -0.1700
Data Index: 5585702 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.5242. Min Act: -0.1700
Data Index: 1395756 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4615. Min Act: -0.1700
Data Index: 4689555 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4459. Min Act: -0.1700
Data Index: 2465749 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4145. Min Act: -0.1700
Data Index: 4571729 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4302. Min Act: -0.1700
Data Index: 412562 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4145. Min Act: -0.1700
Data Index: 8220698 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3988. Min Act: -0.1700
Data Index: 1675107 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3832. Min Act: -0.1700
Data Index: 4550049 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3832. Min Act: -0.1700
Data Index: 5783594 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3832. Min Act: -0.1700
Data Index: 2356317 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3832. Min Act: -0.1700
Data Index: 548887 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3675. Min Act: -0.1700
Data Index: 3294253 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3518. Min Act: -0.1700
Data Index: 8537083 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3518. Min Act: -0.1700
Data Index: 3474988 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3518. Min Act: -0.1700
Data Index: 2634048 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3518. Min Act: -0.1700
Data Index: 7730821 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19