Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.4465. Min Act: -0.1700
Data Index: 636805 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.3840. Min Act: -0.1700
Data Index: 4674811 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.3527. Min Act: -0.1700
Data Index: 1838010 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.2902. Min Act: -0.1700
Data Index: 5693013 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.2902. Min Act: -0.1700
Data Index: 2498927 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.2590. Min Act: -0.1700
Data Index: 4670539 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.2590. Min Act: -0.1700
Data Index: 3691712 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.1340. Min Act: -0.1700
Data Index: 3504481 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.1027. Min Act: -0.1700
Data Index: 7853113 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.1027. Min Act: -0.1700
Data Index: 8391241 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.1027. Min Act: -0.1700
Data Index: 4981957 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0715. Min Act: -0.1700
Data Index: 8678023 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.1027. Min Act: -0.1700
Data Index: 568354 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0715. Min Act: -0.1700
Data Index: 3372562 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0402. Min Act: -0.1700
Data Index: 8221859 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0402. Min Act: -0.1700
Data Index: 7043745 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0402. Min Act: -0.1700
Data Index: 1785885 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0402. Min Act: -0.1700
Data Index: 1380691 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0402. Min Act: -0.1700
Data Index: 3619870 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4465. Min Range: -4.4465
Max Act: 4.0089. Min Act: -0.1700
Data Index: 3610494 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19