Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5541 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0609. Min Range: -8.0609
Max Act: 8.0609. Min Act: -0.1700
Data Index: 5476254 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.8734. Min Act: -0.1700
Data Index: 800975 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.8109. Min Act: -0.1700
Data Index: 1901513 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.7796. Min Act: -0.1700
Data Index: 3840277 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.7484. Min Act: -0.1700
Data Index: 2417253 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.6859. Min Act: -0.1700
Data Index: 5509591 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.6546. Min Act: -0.1700
Data Index: 4104339 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5921. Min Act: -0.1700
Data Index: 4091677 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5921. Min Act: -0.1700
Data Index: 7618758 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.6234. Min Act: -0.1700
Data Index: 223990 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5296. Min Act: -0.1700
Data Index: 7322432 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5609. Min Act: -0.1700
Data Index: 1392040 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5296. Min Act: -0.1700
Data Index: 3782168 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5296. Min Act: -0.1700
Data Index: 8273850 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5296. Min Act: -0.1700
Data Index: 821877 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.5296. Min Act: -0.1700
Data Index: 6946124 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.4984. Min Act: -0.1700
Data Index: 678467 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.4984. Min Act: -0.1700
Data Index: 4050951 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.4671. Min Act: -0.1700
Data Index: 3914100 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0609. Min Range: -8.0609
Max Act: 7.4671. Min Act: -0.1700
Data Index: 5827596 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19